From 9a9695da962853226ce909cae6d70c0463648ee5 Mon Sep 17 00:00:00 2001 From: souzatharsis Date: Tue, 10 Dec 2024 18:04:05 -0300 Subject: [PATCH] update evals --- .../_build/.doctrees/environment.pickle | Bin 2736624 -> 2746215 bytes .../_build/.doctrees/notebooks/evals.doctree | Bin 842682 -> 847333 bytes .../html/_sources/notebooks/evals.ipynb | 37 ++++-- tamingllms/_build/html/notebooks/evals.html | 111 ++++++++++-------- tamingllms/_build/html/searchindex.js | 2 +- .../jupyter_execute/markdown/intro.ipynb | 2 +- .../jupyter_execute/notebooks/evals.ipynb | 37 ++++-- tamingllms/notebooks/evals.ipynb | 37 ++++-- 8 files changed, 145 insertions(+), 81 deletions(-) diff --git a/tamingllms/_build/.doctrees/environment.pickle b/tamingllms/_build/.doctrees/environment.pickle index 095cf8d5ebe89c7e72d478f9e580af406f2fcdcc..5f4386745ef0639d3059b4d27140f91387d33d9e 100644 GIT binary patch delta 297103 zcmeFacX$+4`#jZP6FLbU6r>0X1d=5rfrKU?1T6Fx;DCyN zf`Etw1Xo1_R0L6~N)b@Nih`inu)g;xvoo{1iShgW{jT?q_kFI*XUUw;-S5-SoVhb^ ztMK*7twP1Oo$AUH9FxY6DVkcCnqOEtsc6+=rLd?pcT`c)_>$DzDUO1YRe1R{A*MW_ zbIQwuI;(zNg8c8huUpo|b4khXXE>db`>zu{a-G5MzdoN3=nQfH^-V=br|ACcx7;_& zU+mT`fS{MHO2A9osxkQc0ZN^)#WhEilsZcDM>El>j!C1-|LH!ad~|jL{8kSovOKSQ zXgTgKmp{>6#mWn^R6eRl?eggCuK4A*)duBMCn-pvw?Z=Ob0yu6zw8JDb)>^QcsrKTs%pIt5K z!Viq5eRrVA?Pf_8zQ^g03-wUmcX;9&sjg4LKG~L7Aq;2rvc%x59+oKF=5Sa9KA3F@ z5LA4)m!%%QI#=))B=YZgZ0~Cc_Y~bT#}X|xV;q)b1Ba((3$-k}@@&ow1A|mIgG{`2 zp%^I)VifapfMQ)wON1~`NBj2^?z<27TP~#-+!EIdG@ZhzX7vQBnMcAR0`pSxh^P{s zSSTj{Ziprb*gnY80>|~X#0hH&T`N4RH}F_(z^Ib1}dLk?`h}#~|X&_Wan$`or z?i@xlxjzV4JHQf)x^r+B3Ksr07=E1^K2MlVXzJio11%Oja{$uY!6)tqcKaW&gdrCP?PYrG#<7Dey@bmK z?1l%x&hI`73)bws$Vtu_NLu1|2Ze@%8M?}g2Z60?23xG?4^Hr#fglqfy&4)J*vluD z*2X6XT590wgF&Zx4?@VI@wMxyp-=~(84SMPjqtS#s4h(k$QgBrWkx*0Ut<#Qs z&=QL$ED|J|?>UUVJE8YoS0)UBL@(CqpBrLHgXE)Poo+IJ96!|Z9gg_|r3f$JiNh?- zf}7N^JEf>#GSSpNYBDHqA3M2ljDr{gWu=oG zg(YJ_O==2pL0-{R`_x?f=%T{Wx%soFTUEAd)~Wu^$7TF!6M;C!q zJESYEU66dE9Ha6J@}XLcwih}|CquQ#h1kfsxm#Ra+3AU|_U3_&f; zg9Z!&?-)&qCgej~om81dlH`XK>Ax9>clp30AJI$}zkYJEslZ#WvPAV!a zO@^d`45#T!`IA;nV?*2g(US|b{DP(tQh##MWG%~+Np?*tB;rWd;27g5Cc|&YcCA_T zaDlxPhaC|@|KE1PkpFv5z%Q+nYY88@8zy{vtR+a;iXF0FINs4h48e0`zgQSbY?S?y z@Sgo)4RPi$OQvv>^yA54zfXoio01pPD_+Z`8!qV3ll+C>-7JF>+-0=0cO^M2Ha~oC zoFyZqk-NwbXPpzmTx-Ty8VEuJ4t-8Ym124&8_FGhS^jjtA4?15Kck_i3QMI1QMQW1Kd{6&UsF}<2MgvY1wdlN0a36CF62x%ek zjE(6&&}6!wfK2c~3Qien4a03?{H>wu2(Or4ZUb(x)JU0WarncCb;S!psu}8fy!9oVUv&hmmG|l2xt8Q;lE2aF0MYV9NVAL)&ffU8`g2zm= zMzm;SFlvoItr=dgOJ0i86LNz$l#@p}6M;IB_1%`d8f4()>ruMvp(U0!0(!`TcQ-(d zqO*w1zIpwiW;hM1WlRRuh7$S6*#)P^%Q3aH0ZC9?1wb$@2QyS}ib4Y{c*FU+O=5ij zjk;ooD>N+Jhsx>r%Vn0P=rN{V?Ml?^_;mTLMK(>f;U21We448^n-~Y(NVUD=OQ9!z zS#E*1piy5_gKu#7PVE~>TEw+gAgjFv#u6xnq!+z*$)w$FEZLsT#F?U*c1PBl; zcRr~yKY&^_jh{%;e1Mxb35?6UaPkKRWfd#5fH{|giU9!<(RCjn_lU4wX& zb4c=rep4?NZ^#g9X-;;7d7a-e)iOj7TDfXWw`2?W`53=Y;Q}7@u%(6aDKrvV1#~v3 zfww&jt3nOS(^p3OB{*+jp_gh4;!RY&8aQT#B{l9BAXywVDR=Ccq6v=t!d1@S$b$fQ zP&&Ohca`&Z9QvjbBm9Mz%&^2;4K3QJZ^6g58u;2CDUv9m;(tyEb#Y7#3PR8l)6OTZ z)UrzG5AyjSe)PB8>wWMKiGB^SeVoNV#Qm^m4b}~1Pqs`K@^z{)8r4_>mHVMaHF%0; znJ`DE%GIc5=~Th)hds;FpR8|N0Jb_8!vB$8ne;SnUAU_+Wr&IX!jn4JaT?bfq{k1l zI7!{ZFSZan3h}JVuahaZ7WM!|VpLv|GYX0cbLjH3OF{+K9oU?^YT(_&EMcyfGR1U% ze0-0PhLyIWgtX`BZN*SO@d9Y3g%dkY)Uo5j4x&x?2ruj)CYHBe8$+Youbt8`=v)oR zM4R(0xUij)5at!t>osuJIx!96SezwBhv{+5o=UW`IZwJaW{LiO=wuB%aSBS4=wntz zK&eHSg_by~i}<^>X25;-m5@yKgMR?seE~S3tN5waM*gJZ<=%NQy`j0gfFrw!9b|J# z;<4SpI}P!~*9AQ#Wi2Iv#pF>AY~O?8u=J&FH; zTP*h%W)fgBV?N(djG;IT=ME4z3k!7!Zaq*8LE{5hrJFHOd|G(MP}<{uF+_N(eABZH zaNqV)4Lk?_Mr#9DWvjSfJS^_s|aJTWTV_1s{w6B53{aR-D3SR5)g6z&iSDPiA}2*qSC(<#2fr9;K9 z0Sh5a$4iERaLObMzc@^s2aRFca4|tX5AoA#k5k5Dhl_FeZYMwQN+SkVQfcZ0(n{0l zFVZB2(A|y{GU?7;MJj+H(^e4OY|g+yJmDd6CW2p5hp=sgJ1k9I!$yc>h3Gbc9@XSF zSf^=;%kI``j3tNIPUwWsbn|oDzEZcnjcYL}M{T%_KSzP}EzA3DX2F#V(B^@7(+;Vg zYxHPH2{w!eV$-*XY7D8d6tX*Z!_^TCjjm7cNXN04;x2w8%LV89!`;3AitU;4kCT6+r}rVLcdui&Vcm?9sLYL zYc>uK{ynEK#FE zOo>{XB3Tfl@ql<+6n^swv9ZvV@J>gaDna*~57l-!!wg{`x)Jg@h~QWsY7Qnb(j)SZahq+$D2Yh_4H-87sv11>t2{EgNs*bn0~tHt{GyH(;u;Zr7U>1ud>Ne7Ax zbb1QkApA^_ZG<0n5Wctux~#(?WM*5h1{?Ze1&h=ovS^80VVFrMqDS~I;I3=Mrsi>5 zZ9IRim?GG)!;099!8qNiCDM_b)oZ%b0C!jiGb=K1!zrXTB|>EAXd=cxYBIn zq@MJ!?%0E z_;K1+zc8lP0v!{qVHVfK9lF~hu++yEz@P_XrMf7#a(km(Pj3}#3uuRgL-&f!Nt@xe zb_Z^?U2Nnode>BRW4qYOU3Ae@wCx44oxA9!sc8HTu{|l;9V?}wZA>jK9lmGjpbcie zV=?p*_*!_=K`oTwGVs?&BcU>_e>}OxonlL&F+-nz3kKFzfL-tIgqi?(mi~&^Lg+<^ zXwYrA!yYjpxC>8*|93i{9lG98)iGyvbQ}r1@7mT;e!raJ%4BdIq;kZ5EyjbC#GtA zZg>~}z7Ndh)PH&x?|TJezn?4oDpOdCeW+|21yvsVhPdBRzf^ylv%X>qe4Jto`~$Cw z=|VdV+PW%e;A`Ud=zfJ||8TtG5DXjd$1`3R)7(#swWn$Op*m>TdD_#@j8E5SPnW(S zHg;pTYfrNdFupYZ`&Xscj|aq`(ED7k4;lUYc>F=JiTmkS+S7W6#AfcN_q3;14vDGm zry{;K4<)WS1dZ7Hc*S8D@BnYB#WALZ7Ku2edXd1tFGMQ7GY`(H(KfZIYKlj?YK%wy zx1l2TCMxh2IHxM~r*Dg23b}aV5vYi85(@MttuIu>BVqtN?|uYYWnMhTqc}L1%7uDr z$7iNOdl~aCmC=IXvM#H7k_dbI$cf;bIp71c8R#-5?=g1R7ze9(;?5|4j+ik z(Iu|s1*WAI>vZ+sW8M4&tZZ~6e3P-d+rNeoYKn7Ks4>o;o`8@&#K1HwhE|1Mb5i_7 zn2aZ$0-{+4%{QJF0|F;g#(5EV`FvY_(kyY{at|Od*mfE`z>A;rE*^G9jMs`^@hA?~ z#4NVqtS4+XoOBlQh4XsP0}RjipM@4+awv=Wq^gV?`=R)`@EtSmt|z1K@X3#$t>ncu zuy9H2jEULsXu-#@Lc~jIn@ZZ9gGAsZ$)=J!=OD=6akai-YH2~v3aw_42N9Nh+CI=~ zigG_IkMfy&q0xBR1+fDxT z3Fb8V^Ov>fewW3DhUf2U&v#uGlMK%oj-@Z;Smm;Q3dd~&&3bW>M&;QdN}F*zSs#D ze+SvO8u$1TjL^y|%w>LGL6@eLy=^E9UQHE&R<{=J_k~ysf4|8VNS10f@Hqn*gpB=K ztnX%Y!(66(BW92?;x1uj6;{0Ujrbl431?P>g&V90!Roi5sa6(mC<_b;CoY3#<={)U zc%q_)YH2{hWMSHO;0LX&r=d*eaJj-(mvf-84GgDsMvJW@teUZ%3Um-#RLbbJ;7+8P zYKu1@rUlmK|hG~ z+>gITVG=CcJd+x_0e-snRW9o)yt5Pobu6PL9YO>K*J$xp~pY`p5>)8C+hWq>k zdTNN~z7YTXBsOp(dgzECjR&y*Rt(2){w&sZvG zzelg{uP{1zf-oin(nlEsEqrA)jdc_K2GD0T=u=fe_x>h+iS}_99bjs!f5NzJACCDQ zMs!-yX}u_L9~A~!efWs29?3}!1Un7H#hm`pKOlTs(Jy+DPJjBSEzU?EgwtzCokO2w z(b2>#j=*!?w$;LSj@bf8*SwFpa8FfcE&WT}fs)`<8kuD_p=<*=+a&zv-(rfpu&YO5 z@jr&b2Wg?AQAY6ETy(-_CwglF3d}rKpOKOXf102P5vE9&)vR8m@duru59?4vs>4>c zS1~qPyjM_FwCY-jr1r3r0M6qb>W-?=js2wk=m_`C2||@49KnVDQe*8Y9@~QnZvzE! z7Aa9H5bkR5Q--IgMlIGJ+5@BjpqN!diq|MmZF5;dfRsYYsBhk?O3iZt(jnBk7He@k z8M(B^wjfxB)XE+(mmLp+$-Y*WZ!Vi13`S~YGtFfgAyQLPMm5W#OV5`tD=;wQ_%sW2m>hUY}GO1L;0um9Q> zja!CGAsX3qGspMBrG{D&tfbI^hnYuhywM8IOTB3eAa2QtWYO;)X^Q@)TGfoc3+PDn z_cD4d`n##hT4k+K3!;CLBj2wI`Fbs>0=DF+vu;J=O?9Mf`15uo_=!Cg?!z1FK<)h! zud5BF@`qvC!!C8Cy4piH9K?_}>*&aq+QYRrDHVOmt-oHCPW_@FfJ5=M22u-QG$jul zTAMeE%YL=Rk_MU=Phs4L;a zvpe$NV^CxVD~{HtF%aINPgLc5xk`6XaFJj8Mm%4Woi%WX%By^593P4L};!(+}S{CqCM=PJu)A>1akBQ`I=X+GkNzcy?eZl5Y`nP`dacl|*|C6W!eOpt-zn0

|rw>cFTmn`C+m3AQAR{>Hy&iXym}GlrY0tGExi*W#Y5x zQk%Gez-)1i(eRd1?j))@KU>C8_v(g;se8==zJubyId}p~|1cKkToupg zi;HMLZzIB*BTd2wEu<%eb4;T-nUX5NT4*LK_kI4wpe6THR7awXxPA@=;x?_JG&G95LeWUtrgM>_n4_L+Ee#ct z3QEE^Abh8d6pY$Ov0$aPm7W(K(0NKbbT$JR zXWXtGi0R9fC~POqh80y^>)7^C>f}nis8eeMkGGdfghveoNgaToj1%niCRo`)8V#@i zx+O?2>6o=#rH8VZN+f(SbT63HEZB}E=WVkMHh`Ugsf(|UkOHL_bVlG)-=R17ork`8 zN2yipVK@(Ot|A~$+e3wg;`F2_JKoh%YAPI~nv*jzTE(f*#U6&&o}uEvrg)o9QWmc= zi7ZfiJ4tcSvFmp4*6FVEaCPe}^@ggeWA^BnU$}4n?hL-U%fr>Ui!|J-Mtdl~7q9OE zoiU7_4*S#NJ7K)Wy{xl?s}8zKwaM%H{iSp~q$|{6*mLUvb=Uv`F}_1!&gI?;pCEUUlnE-i)^_I1Xu z=$HwFadYI1W|d0JmPWt?+zrL+v%%6wsdUk$lR0r*j#Mwk>6L5-)(;X)b7G$F+%g1| z=2p0CXO6T`u{k^0DLDxBQ%c(r5kG91P?GXJ;kI{{;qG9R|+o83mU@43$#gtvRAwP3=Hbh3-3$L%VnQy@sV`lA%cJ zAw0*hkq-fOBgek%i8WU7*BQZiLg0#F z^}6;5kb068>>2?D?{iN3bWX>()X0%i88oLPrSN+r0ehWeU-8CfIHbui9HrRv4#3`H zSgekMv;&U58##ki(9qq;Nqcn(-~&RdomYBuloX*2y}lVGwT!MCYYwG3Sf34ws*6XC zmNM`+ANV&i_9?IFBI?GnXu&UymZ3JZC9 z)<0Jo4=2`ig4?-3FoYBA_ardJt<*sE(paFH7)yc|iRDv@4SzothGO$|h;%^b^%!H1 zKOF~Db7RZFCDmEGBC3|+dTcv%jjrq`h!#yr;4@r9s#j*4)T6`-*YG(b&E5eu#t}hYV z6m5*~icb9zk0<=ncp8fKQCITu!sZFm0=)k-{|r2$5FGY1Eo*`|6iTDuV6HGlN|#>M zxdz!;L+UJoexe3GQzF&JPZq(HvL1uJrbF!<+PheXK2j{r6IwCo>pHZB#&sfSP{VG> z^+>#Nq7*^2(nI9Z34f%C#`7j@lGG2fjjFs~#|*KvT7Pbm^tdpQ7UQKQAgGW@72nXY z;k1>>Vz<^>JdXE?loIt8uW1Kn}7%^Sz;SrOiO)yab32o3eZg~C_ z17O`0Nba|A+*AM@*mO31EGvxWUJeE%aPu_lKnvYjB)rLxZ1qSn2^=@n@h|8(+MwO9;lHGo)H5IF4o^ z9x($HG3DQnGo)<%-3*wMG$uUwdqwZ)9Fp+FGMF5`HWOAKI#S4*fpU!y9nc=Hm$-2{dM$rc3L`2J z0<9l9`6$#)EkEu(3ix?B75EKJ^5UrPZa4lXyx;rQj8dp^0ifU&@D9E(laQt(SJ=1cpZ` zc+(oGJ~J>9w_5-mZ4`L~_gBH(56@WuF04(M)@IYK-3y>ao4~X?qjPo=?V7=5VzA^? z#^j#WOCMo!@$5yw4fe;0in|uU62Mw!P4C5E&1$aPhdLdF&K7pz&?V3|yvVssUqZPU z_1?7v^mgiciw4zdQwv$+W$e`qzSTn7f2ovY{kX1Im0z}0>H^nck&wCve&=*GKd#G$ z67WmA9z&6->Tg*lje}tf4Pd+FV8k!XYqOV2xd=QSI?yjox}ft7uE#o`UMm0_fYYA@ zx6N81^+NR-7XJwaD2}1Ti#j34j$SDZK&?67PxRtU&NsFk$OE7pQk=cbWUQ+OMSd}O z_Povq4%d)K9xVs;AL1%Kv+|)z0-Fivb}L+U?g8WVaNtwY3^*$vx&@Yk$ugMuxsDU@$i8w@ob|NS0mdnAi1dXHvDas*_3hIj zD!M-FKI*K8E~k}&;7gsL1tX9Qk2JDx)=Mpgeg?9ybh6%D&cbJy9KAJ-#D|`N))d}x zfM@mke={|WmmVQIBGM9gJL>X-HO|8mO7BJD*baT zF5e7eo;3uX3|Bik`l1M-947HnxGR5)G(@m&uJ4s7A3qQK2QN|y#`(lMAGrs&o9p9S zTa_qZ#M8C{@tglby!?h=BmySnWmVC@x10pCnQPiMDH2|D^wP|*o`&PzhziFYc0#lL z-gYSp-gP7nF|LEWtE+q275{={f%hGmL_B;4cACf(}az{@3Z zJEcx2q=BjK9MdWN8@Qg|DZ$ku{tehm?1nOUsW@(z)C`@Y!ROs8Y-;U-R-8owzqm`f zfl?dLHc>pTv*pEKSHQk~TUK1_14A))5UeOXiQ|Tb)@8j`?LE*}_w%-4@E)lf8q93a z26HELZvF7pJyLDdk6D0|UIriaZor1u<6oAZK~tCpxbjIY8U zP{S%Q%fMy~mX%TQ=$Ko2ra1BQOv{iXEoRRRivo`!6d69_S#glD_ z8cmTf*SXiFX$XbK(-gvU4uC4WWWxbzj327YO2l)zMddDN1q8vG7VnYm^ey%X?0ieI zn%4kZ;e~HWai~o^-d*e$Biz8oH=;7*D_H{U8c&x16X_CQ$oSmpDR491r2Nq(o~wTs ziEcJ$8eaak^btynr!}b#eaaU4%JqDAzae$}9cetujmJN%6`H8oml%stU=macpRY%i zurl-OQUCr>dp(LH|Mm5#d+&m$wt@}xPzd}Q-X7V+RLI6YE@?hS#B<;e7b(P~1Mx*P%9jAVuSd<5D|o z&4wQ7avP654&8oKL)tiMFEf9pCmNyfcz3d9L-y{Z6)xm3I7XpJ*sL#mA6mRNP)NMj zvJw#J^cWhzL47L$QO9jP0Vj%_4cVcvNqFN)SkrLgnd>asQh#fOx05Vqq;ljkJL#(KBtqfgqzdk&oo3Ts(40g~8+8`C zj`Q3JA613?;6tek`ko`ds|vaDBWXRdBrtbLxa)#J5U5K& zAO+{3B?Sm|BuX%y9(bV|j?6m`+fq3RUfFj3ytG~DPei6@$#zZmBO&ncV@?7~w(d*^ z?PN$7iquYqWM71Zn@NN#e|4m&Ds;goFfm+UKtEm;y7-b*hBk74ZquEG3opZgu8myd z#p!tYB`HJH@6rMi>b&)4=XFW=_bi-oMe1e!(A#;RT!EE_PfX6ct~-wqcsTDv?!41x z15aqq3;j%bTln4JiC-%L(rmr|D&$~jB0H!f<4xBk_aSpPM+&rElUAXGM0N%+EfF7{ zp>_@+irSnBxaoDN6)7anfzcJ=qSeq7)$mQ@&!wi;p^09JRrY z&Ka6WGYd{E87;Y=0wJ-$H*g>H7t-@+E;o6$Z{Vgcp#fdTF>8EdD6{2XNl%~(<`!6j z?)x<~WEJ@7ucZv~l=@?*$shM8{(G)0{YI*5{oLChZ+!#j)xI_R;|tv%gu=rgpL2g) zHJNZl^9POW!5h+U0p8pH7FO@zCZO;13^3z<_*NP#Lf*Hnr-^_^6VG8?hRssq8Z z#!8{8!aC_EfB9t*eOG+v&`u3U=K8l7>|a&|ZrvT28*gX0=c~Z2{y};i z9pZjEru!+7YHD*H!W(~t1{)C6I|oeO$!%mBGr$`%WC#(+PkWW%<#(lI?XcG<{LWpe z9xSte13%gw1Xpx-@NsGSPtvObLP>PHlKh7JBE3$2e|Sqx5BbAA)#P)aTED`AH=Iut zWWGK1=dW~(ODF$rev>AV>p)0h+F_}NsFNoqv3bfl{ZV`po2PWU2VsM2K{S@qc^%V% zk>U2g!w6p^DEeJ;2}5)O+`6V;2pYtp%l-g`U}!AJ+7STbw8kKxTXg3SX`Qt+$s?Qg z;-~(UI+1I*1UW@Ja`B0-SSgPEOPY`1a%y_f)5X8Ek$$-A-e1ys!Me(u4rq>C z-0g;vz1;1ckUZS_nK$1*Bb64y*OYHK=liM7_p>Ct`wzLcFT%@z$Sq){ktkF-VJ%%E zy>gAr6kv*Q9;ZDhw?-k!wAByuA(z;bgxkkJq%ZSGU-1Vg?X4`*29tTJx3$O?WKBx; z2=#eFQ{tdtxfx1=Izg@jD-M=JM8oVU z9X}B)PeQ|!@ehkEjd1(Ju{Cgqk#b;X{T9^hAA5ivHm8Bg#|5E29;LgchRDN%)YXCf z2=}a2zy>ZrCs(f8ecx%CjV4lI#qhdeJgPphKVUg5+Dd8>6*B~f_V>`UufcNA9PoLcg9w2Jw%mZ8Mxo60YB-P$x#7SQWe zJD~1C>HwF?0V6ydKtap_d$}2q!aib9y+`S|W*zxs*lYZ*j%*LuMb;TA;C9oIem1-B z>qWD0-Mal3`3KaG!R1u&O(a-?Phm{89gu zDl1q=$&b|LJ}FgIFbZN3>dArbn{)fd>wY)jc-49-UcPHB@pgN}Rk;uBff470Yi{q~ z6jWhSN^qwH`2|$MJrJ8{Zl>s>W(ppiD6bdR5hiWWniRH_pWle~Q~est_3^q!@@{K| zw{RNsSIxrj*M(Q$Pm|<0p<+!k@ZHJyiiYxXOu4U3mX}#CR>J+7nfn7e_luM}y2wqF z8_OZ+92a7MQ6Znf zEX6QoHyD*Amq({O9GwvdOVnIp1JtN+<=rG6+fMF}KB!vBXMd$izGqa@vzMe8rsTW4 zTK%tjN!Pme^49`fh)|YQ&2Exw`AuV=-Q<^qk={+(Ji1AP`q!D6zI#an?p@jzL}>S% zlV~iN6WzoR4FkA((Qr-eB=;4NJ+;bux+lh;^eWNNzR2#&@>_aTR0?A8sFTW?Ip6U} zcg^i0*RBEgJwKfz+iTDPi9Zgt$x*SDj7PZq=3KsSN15cCh7-h5wnfoRBJ{L1fXiKH zddd-kbqH5FFPh&k&89$TRH|vt@KzV_1v7I99@kqw1~bL9K5`pvkFTtcya_!F{u~O^ zTOC{Og1OdeK{$`e{0FTxGd-dMm%0l3%eewtno5TYqM>LJvA;Q*pUQ6CEf^?g5{6`6 zgj{BZM|FlTyP_YE+Y0Dq#t<(a1l>agVU;8qU>euEgTNNxO6Nt{3?Rq(7-z2T7Q5prYL`&m9eHyfEo2lL#utuG$XoWB4%HN{lRjc{q>r~AlCN<+d zsyziUH3#w7k!nvx3+b-e#m(&k2;K5}8h?@rKNIlV?B<(va@aQCfjMIx+xx zZCg?xM4xCcLzDqs7hEw}e%l(K?$L6$F<<@M>gC-kv^+deAK zf>9d~)9+#YU^u2<7uLCWU;RxwJJetQF<2n@lcLF25>y0h_WbJ^^>y?;9J*T$a~*h0 zK4d|`8PKi4ylU4X@Bl3d$EOy_2d$AA9vOE5uh=8EGk+wdZU#P>pk$)@8QN(I@{ttn zJ5F|-zeG-}=4U9-U;bDKj!7ir7{j*#5{TY5XC$t@R33#QGgvzBTngRZJsu)x-Ha!P zeq1Uavi9-R{x*JRncN3Gkio_~yuvinz0wB{TrO`zeYk|iDr3E0<@YXBk*Z(aSe561;O2 z&}*Eptdggq*EqPb4t|A$53DwTZ>^SRpwnE9C)Ys939d$}P6?bzrSU$IX|M~N02qGk zy9WkFJ-DUQv3$*X*W1$tYr)gMn?0ST3%!f~Tr0na?lMnHhLStnkj76kDew`m#??AY zWQZfr;hj&)e_8EKymI)Br{s9^fuKhC&Qo$MN^YX1u<<}pLX%1k1T}9$4+M3j2ZDkM z3MPzjP98JP>(dq)#B7^WQ-tiG!CT#}3^$^}E47>Cblh&ekBm;ibJxp{SqFQXaU0iu zM!p}7Xktp{Cc29U<6Y0lPT10=ymK}{-M$|m-UfqW1E@dPM&3)`vq65uI>%c^$BlA( z^n_VPQ(eX!{MJUfP?$qxw1MWEu*d5*LF6>X?`@Kwv2OEbJpEZY2kkO5Zl*KdhAq#@ zv%Cq}%e?3?BMj$n@)`-7V6`h8y4*(177Zm^nDK@unvSn-mMg5+y>)ze3mAXHtYdRs z$Lsj_E%HYA$^don2hW3pKVvcsAWcS-t@21~a8r+5yp6YPm50K6DZ)0r2XCQ^2*z34 zSYMNq4D&2qXX{wg4~&0>ChH0e?KMw|Giy~ zHC^t|9qciVL|YL1$WS>Zy8{>jjdC5rV;;QJKn*n9?m)_+QnbM84!KpOZ-#QzJ?PuW zmxIc7$o(yXgD^{8vs+e$doJk43I%JCr(=C}RMVT%j*2YfZj<$ICuyJan%WeHI{mBr zIj>5(sxHi|A{@L|p5aR^yjRYsW%{Di(?oarg=D;GRKq&>_q}p3TzzKJQR_{g#NGE* zyEkQbw-cU`9(T8ES~jJh9z#Vey=u|NY^GyK4Ze6i;}v-W3}J}t=|`1tPZwm~yDSZ* zu6oYC-IO&cFT3Pr!d0C>?51O`;5o0tL|=nmg4>PZVhJ~IvAYia30J&kfQGy-uRwA$ zHefmVI@CG1B>!DGN$jDMyp2Qm%c<4sGz@z4PUF%2@@uFO7f|$u&ldURH{>m-9mgy@ z07|r`N=Q9*B{Jby25DJ;I3V9Z_j9ax5U~9jwwDQ8?QYH>f@$n}>!93EKogmWS{Z}f zLqg9W@?+Ht56gwt$C`OGMdxwwThQDsX=YjsYN~U43=Yl0DD|;stSvH>%x%VoNQ2&% zA4WTv9%3_{avL=mw|WN>W(#+V^Bs8{dW&P5>)3-Fd&G!6BIl!v9NR+2o+H@ioMnAH z;awO<-C;0nI|`n@#XOy%EmOGz@=yOm2w6nzMmxgR^X>6T*9ICuJYs9y2Ja5(t0qZ2d{*tZFB-A&Gc0N1cKhEqb2m)wYAKiXoX3 ztGQJ5(P_E9gkEo6_qgAUt=`K~ftSYrBhN=CCr`m@HnKID;<(Zgv zSKeve(!#3&BS)do&K9%*)AnfR)~TWSXG;qb4ON<_W54$G~kXvMKK>4IdM;4@H7CmR_1s44{PmAuh`P-TVu>`I`|N+0Nc;Yl-?IpF@oay^dodA{2&YWXpc>S^Rb@~Oz%$06 zl5ODPX)(tAas#w_EwyXAq`U*Cms?g@#jg7Ykfu7JrLl^6Zk$mN3qymJtXU#eOxrk1 z3{~n0sB=qP)Ym_jZIYMa6@RHwm2IAJp;?~1D&IU?8g1M+8x4fU)rtr3;xMIYvkkCC zMCQl*@ZSK!J|O_L+T@(k^TH*@f&kv!VPBz3>3T-NRLob1z3!5)KcL7GB)aTovj7U zh;jaz}s~wX2DG4%#C4ojk7C_+&g_v74!3gc4fek&E{Q+g;KH_L%gXvq> zds?#Yqm@kwLAzSAwRi*W#g^<8!6utx74Sg25^25VtusAy{WBHj-VOXk*ZG#~p=c#s zK)0AM(NOd)u82{ZBTY<5tl|)?5v{!XU)mYQv@-R-zv&VpT)*3uo&t(!Ma_{6MPaSj z8sDzEU?IpMGgt3}1_qOP)YN*)B>{DWI|0b9PILo>@9KoP+B8t=`&s*XD#=#M%pV#b zg5OL~TB2dCv?X!luFhcGI#Kyw?&_ccv<>O&`Yusfj8I=@Ki)pr->vSkWTm$sDx-#^ ziv-Uy2{Msh3J`(w)08ZvZGD|4f2;$iEfkZ44BS3li9l;w(R+bh&UB?*KwG&_Qk#HB zp@?$H#C@9>xVV}q?a@KTrS?F>_F3IcZUx=|uaJ+=_i3t(@Ixm!*Q+g*5b+J}TxdAh z%9*QvrV=EeYaBG9C5Zl%MOKQ}Szc;I*Na^5wp6AI!f&`kYp8NRb6i6cj!du9tFzW? zV6SQ1u#NJPU=45Wk){{$*KL)!MAHYqV+e>YOfL3^H=P~k4U2Y4EPru2kRIxUuOZ_( z?UckYuP;e9YE8FE>e6iz#>rznGLe{PbB4R*_R6CI3UAG(8T2uWxTjZ>T>)9jT0fyD zPH(3~bfR?_U1-IvT!Z{RezF4>ioqg+L3JNWxKwKk6Ltt1J%8Fzbtzl>+~ zR+^I1{IQg zMEDEe?4v}688(MoFtfM2YV}pp1YcS{*iWfz-tPMrFX*S(gqxZ^{n{xFwJiRok}Up( zWih(|)I#b*hUa_#nkw8;w4b~BUQ8}|S&#S_rp`$e=L&9gOvp9P@<8lmBY6F%0$kZiOQJ^@O4^Q4q6MfBv}Ex}RzjDC$*1A*!I6rBpk1Z+&V4>o zISd~TA<$a=bn%APfbXN!8KrE3S5+v_Tcd#IIk5Juk`$s7eTdUWD__H{cofuQ41jL6 zVMBpA$wbD?e3z#&V!rfYB^S^DZq6^Lm9&oT;>!w5cyM}&#Z4J0lgY2|M%XzP_xvr3dip_EYQ*S2Nqlm+J0HSHlg zo*}=*)b==>quGPcPE#(T0{Fl$c~S4mbQpBLh&$?&s&;T^oJSzzc*v!Si@;C;aj z^`g9hug+3>n@=I#*ABORMCp!DJ743~zghIIJn~F7;(0e`ws>1;OUMVz(> zCKNCEH0A~T@}mD_OdSPIV3<$GX~wvmiA7*9-uVXCe#59q4r z6bV^h^0xNnElM-t6_d4{b?TQ`K)vWL;DOI8-Obh>$1gmubP_)BZS65)ZFT!v7(1Lv ziEZLJcA$#coG;;E#@Mzg>2OronD$=ApqJW{;dMClKL@sXwpRaOWjnN1LI+>H z=wHNyFuY~E5>w4ihm0BGGQ65B%??+O7nC^yeD{w84gax2Z?SAID*bC%<2!iOzu9{r zlN)z1b+KLbc*S>MgCj4>3pnOwrKdSy9r3i6m2RlBPh&e^zrEFt7dvWI_OjB{Gh|dZ zn={_^)?OvS53bcne+NvBdQ~^I&8x~;e`~&{sdRLZXjZrc4>|w?gULP>o`??~sJ6n8 zU}|P)BN-JgZHX!ej_?m6CIOA7f;H6I2VR&O+5!{ zRAHO*fNSh=1^EdFSXw=KLQAVK{MrfSA#`6BTLbQK5>_VL^AR|#OTcS8N98*B;gd>R z6v{C-0E6T#a3*GA`?kd7rmmwODN7Jqo`uW8;0|xSd$-#C0iLYyzvw8&t?V_2kVp+T;CON33?{gZ0^t1|Jj4KY0p}EiKIXX7p8@VH zcls~`4$6J*13aK(c%PSd6$D#vXL&TD7jV&a#co~^yNB0bS8Ag_vb1)eEQtm2h23Al zCq6%lV}Va?!MEk&XukSEzIvwVLqsPVto)RJuG~hqv*^$?nLcHUNP12>eXfB8;HzIK zGfk_d86C|_Uvcm^U-}vg;@D~_P{rdtUn+G`Q@D+v9LqDDJti>FDh}8DN@-l_*<+4^ z^q^;tAO1>t8ljwy?4(}4x3h03pZZxJB+3{Uy)NLvx0J@_R%0{)v1YU1*oF~?i}G^e zOHk}aQsWXS9C-e|+KmTkI}gu^^_-@UXEs0RdiHzeJVFn4WV3`FKWHsRxa<8Nlpp-j zLS`ZU{ujtUFrF^<%*V>F%6#-}N4mFCdo$8sD(VO=EMF1a0E1TY!9(FUr6GEmVI$u* zU_0yB3cO;F3g3+WP5In<*xP9jZC2}>C;0Do#49$dG3bO(7s0{g?_szc`+K#=k_~Cn z1{LIw%PY;D;{83uu0&Ux^Dut)cjXW|%={(Nrz~};1!1n2|4@Sc(2v|}xBmuz@)G$U zFmC}pBkc6@DM=lAvewSzOrY8cUE#=27*e~`Zw3V2aMkTJ z&WB%h%RS+F)h)TD&~-IP9WJ06o!L#5e%PVH?r;wlsrx$9P;%?v3{gj*XbyzWTUH8u zMg%uC$SzV0&=G^`;iT%xJw(IYjYKVYpc40|i#f~UF2~0@5 z%WZcuN5grYO3~ErP8`^w3gGcbwHF$~frBVev-`Jyx7&5TwmMos4|96>Qma9u(k?uS z`^^`l@f$XE5?aB5OML_B?VY-z+c1j9sF-8>bJ1c@Ofi3UNLofExXeG9NwG(1-(DS*rF@#=B!?) z3A*6JscQPa_1=q^5>0UJGprZ$7`bc5^^?Trme!}|6nI4oUl=8JAf zy4nQ3q*E!~$#k{5FS>*bHBo?Db3vYVmewe*D?3Z;L(#(-YD4&-aOH&bFjSMSv@;hC zJoyM~RTK3e>vnGkY-y@?g1t?nAxrc;+Kv;OsSaOsPd5X{y-n$2_-$TBIxdLreSdZ# z_CdP$&6LACnnN?h2S>-7tIrD7OWt}tlBsrqk6;+}TBhrD3H!HHXZWI9(GmjlbLDiF zR%(A=bos5+7AT;b>3Eh&;I&q2Jzs))a!i|=UP|F3Q#IEdo z+a>O`gKg9hyP^L1oG0PSZPiXVrL8*0bWC7iH}hPn6a3BRN-MyrWUfRg%g_Vd4#O;I zEvrJE@H6eyX0?5vC$TvzTsPaPqXaae8(V3Z(?N@IIEGf}l63|VX`B(A$4j!HyPs$F z+Nn`AZXRuyu_fBTEZ`O4-A?K?w1ca8v9q}; zfmqTYt=eW*N*P0O@LDc*LuRI6zF-TZ8{cKN61wJI5nFwuJ#L71{-+A+nKGt zBUtU-J)&{}&+Dl+GA}na!uxxw4dBHe(1{%OGR{d8aQ$9tb(gbK=v+&2&$ULBI!eZS zeKz9-VlTWWj}P}!8~D=jw_a+pc_!V9n8D^vp?zRF*{8P}EcEfEZw_AHyW0A~>ZsgD zwHfyrH04}v`lyN^*zuVmD&$~acecCM_f_i%)>2Q$vUG=gkZEA)p)KBQzNp8y6gTOw z)`x=(lVR({d1BPNL?GM+hD4XI_UyN37oa9@9WU;O=G zn0s8Wgz*~&#^Jc)LABWWqqlvuU;5qKzPEJye#F~`s0qT4#J)DHBMQfLhpJ29-kpk} zY8%to$o1P$bs7ou#Nld7W2^G6L7gzy>EUXcpEa$AS9L001o;^6P-~g%R4bh0P~%aX z9@^ZVR4VNi^voXkhgoVEe$Sy+_moL0ty-#HwMud)P05|)xe#}pDV^4X^)2vA=l;)( z((*TK>w!@!vN}8sIgd|`f$l25hpB`7KzFJGcga<|`XVG5hh|hk*nX@UPo@7&)fFc@h~Sp zVAkZEZu>s`+<0|}FG8gNOgO~|Q+a(i5^_;wnB;L6$UbhC0c|qt_X70+fm|={k(L)s z7VR!n0|o1^-WI)Iq^6^Pm}1)C${I_lfQ zYnhKvP!nuUFq{sg;g{5mItI%O?stE!Xg{0nfYr? z|Nc;0?Bd9OUF_O4SxrHkv)M#{6MR-zpXfisG~lZ}eWs{MXg>$OS_SZrDQX-#%YmnS z17Ygh1>NA7uP8>F^*)o$zOc|a2wF&+^C`xFFI;h}d@WqzBhz49Zp~rKb_)C&mhHqG zKIeB#SC67Z4vMb?MCbe4ABHCXJpSroH3xOhp-G&`>*aMl{X0;`P$vbu;k0`P{6m@A z0=~$5Xoi{-?TrDu$iotH3xC2)5RlIVXcJ4L0KDRHwJxsMAXre_s`PC%OSQwiIcJvV zkY_PS;zOQ|P3$%@zgn83RR`k;Z6Urh>%WY69FM5BaKpiBsx@3A2wI*)@n{~?Hju9! zio}q53J+@#3y5i14tJgn9mioHBMYx@nvLDh2zWC7K3koIE^y?>RUv;wTo3JSD$z5vw`pjRr6=z9wbU6epQqM{_C|t_$wL}o z5S@b}d(sSw;2Gp02CsNdY=q(sJQJ$qS;KGv=!iD<2>j7J7$US}GPEQz$}l9+&8ob$ z`%$$KB+=zZ)#m0=$S`bw4ElkGdKwc)8-)z%$wndDAFK8#1P08>?d)-$haafUHs=F) z_hMMY7=X*>tM#-5g3mzzTLRsE91>_nPu7?%rPSKe^`f4}rR(ias9VrB4%|`&@YH0l(}cB9PG(H;`DJ(ob|rgsXisJIlaM&U;cFKV+^aTM@E6{wLh-(fUXrzPqLT7O{S?EmC z7CA@YrAyTK0KUk%Cfg2I4=zzf?Q=U<^{DXq4O*(+vi9laHQpAMsVU~c!h^WYGH}gM zw`+`h+JkykvW=G8i;fl`qhpt=b&L(-*F+ci^gu5*Qh;AFQfN*e^DRMr7tQA?O@N`I zr}eSV#eG(&kGC?uqq-6dGrkH`Mhqp)W3umnc)GdmgNX&NS*b2Tt9r4~nPC-&P=V5A zcucw4z0$pIj;eqSTyoFW=jH0N{%A)pw%2{vBL?u1&b8_X{^&Jc{KV@DKDo-krU(U{xrfD;?0A?MesrHr79_CAIWs zEos1(YFEI7f7zDSEZ|89%911$>0@nQ`q~yXJoP=;cX#B~gUx~l@E>d%IP+m8&cU}1 z@`53wI_rVkfa^c64n>*0*#`fYK&;&w+CL&t+u(23o4rhV;d%8-0d?)omi%sSgGDJQ zqF2(SZdW^_A*@6k)7DKo2=Cqwt6c+olNGf3Sb9PIf7tsD@TiI}UhgEd6v)knwtMep z1A!#eB=k<`9YRa!2@pt@kdOjM6Hrh(L4iSRU;#xCP;f0slOiYxh+;vhA|h3>fQs)o z1~!&Yzz+W^sL3r0`OGSIPG!rml@ zi^plcsc89|GETST4|<9T-5PdSA!lKPxSQyHhvK~W6=(k~Q?&b#`{K7zaF8&huO-m4 zX*_+hBawBVT5DdZbt;cC^n=E6^+hM7sqNLPvAe^ z479`6WQ+J0oiIACQf+2l*@0X9DU+oTiE_`uuMPobBp0Ik} zRVtZ+@4Fz0{jmsqx&ksoCi{V++P-6=seYosMzfjKbn$RVRA! z#4hf=GPqP#dUJ1B%P5ng{a38C=Z9g7yq1X_Lwd|L=`NN&QImdy2zX7(LRF`A_Ju`~ z6T+U%%fuKAO5a5n?F;L6->Orhpi5qLhVBo0JAnKsY^BxtiEgVlCE)>W#g%v{jFcsR zmuwn8qg@3l@0Mg593xEQ_hP0|?u5rQOfbXr$DRoLB|x#$qzjlt-f~baP0y|h3`+dZ z6GIPu5%vg4?8D9cez&KE|HRW$zmNG?k>a9^lK}`1pOO%&`guMN{QQnDpeB} zg^=$p9(V)Y+setJPOW?Mze){t-VEzOYA2Ui&5V45CnlCEx9(fbaEwSx4S{o)zJ<5K zn%HGEV}hAW-~Eq>bCvly>{*5MEm^|+&$)!X%@P(rcZg$zggufyO)2Btp%J&kDiUlI zO1K;5bvMubjvbOwW_nm9xX%3+);mC%YT{Ay(MA4vJa;!tCDjl+uQ*6Z9MacQo=iu>R=b-9MWMQ_1G&v z;BIB93c>Wub%*)xn%XQLdp9FyG}inj*_CTokCew5FpTp99l|Bk+qJLXqZ@0}uj{Hl z$FdnhAPuonPyS8R1Ps9$&)#P@y6SoI)&%^I^LG2Ws6WcM8aGkPlqIuE&fGWic;-Ih zmAS>8B?pPjoo32hnUnm_ea=^lYO5~sx|e7J!kb&%&-G>Z5;Z7(z}jk&w?@SG$y?ee zNzH&4c_!%rvsR||E&o}&nl^2xHm$iIM(aN7&ECzB0a;5uiBE8?Y^RP3P(I_4o3C%X zp9_<5QzO^?+lMK(X$I2m!mf4lxG)pYaADm$t1pq;2*pnHa&%EW11@P@)a#^dKYkrs z$SUNx$jnmx#CENHo=*e=@a))-AG)f0NMt|3>+5ddrAhF9UvN@)^&Dv|z##`b^aeDo zhuWBcC+kL+o*#%ycNfq-J=98UD2R8Pul7)vmLh#*M4S2wp?QnuNMH4@@ZtT6wQIkm z-}F<9-OQ0mEA&?*i4zI*?QxDliv0FC3;XdNr?E=Z=yCe=Ga+nIH-ySDT9;nu*Zx2wjy%yZ9MVicIpopcB<%qr8Nkqnaoh;-a@=`yaq1tbR zG)45Mf$IGi+%=-jQq)MxPd>wYZ_{xpsx9aRIR@=)NQ+X`ZsbGcEzU!$S|-3Vq<8+3 z+fH^vQ)o8R2C3?v@Z-KYQhJbDY{d2(+H#OuoqX%g5%UU`ub@M=g2gpReb5ywa@=-8 ze(v}Qg=2Da{cU%=$ON`IkJHwJ)z##9Khf?F8lnb=?3OY^wR{oZSK(#*7qhDyG-RmS zo>b^BhK%IF9G5&wDBGVd8>&7{@Rtu64IKtsE!Cfwpb!&|(6w1=H2rXx`fPZ-Z!CGk z)fS|Qh{ZSpS*6 zCw?@1Viy96%5UWMC)ZhtA@Sx%21DmuPdHB+{!pc?MmK| z$&*uaKZk}GZfzZXZ;YBr)(Ms&CdzJ_HdcL&9Oy6nT8m6Swo#YP%v3j#uQ?`xj>tj| zoRT>Z*vK8pNtVs0$SuiggA;OJ7qHM$CYVrViw8L%&cxkhuqB*^>w09I`j*3q1pVM)H5gk6z%tr(?O`<(*A@(* zNiDFwzwT5R)=L5w8siB$1iAU3h0i3mQTWbJRsU9$z4YvKwWZnbCD7Oz>Qr)UKne31 zi5s}37&;AjM0F8zRx0A^EKxG~3{IWdC}6i`vO64iEAN&}_TRIS?CU()wCTALQ0K>L8pP#*r=O0@)J_4BqvJd}*%QOc^VX6r z5T>ns0{-$k6k%%Mq(7lnN;H>XKfNH|PYJHqo=|I+CeK4qOwinK__OaHJdd6kXfDmg zhd((;l;%|uC>oKhFbyq;YGAsuz=ZwJWu}o!VO0A|7I|c3D04u2OB9)dgvh(RM8=Yk zoFY%Z$b>VC%R3={kArtzDZ&s6xmvP}`JK3oKYGbnydT6tLdHu2Jxxr)fn#yteN!k zTGgSr+bb+K&rbmJ>(aFmIk-)>47`sFL?F|RJl7toWr zi?W~TjY((k_Vn^l(M376PW=$ejS!Fb(V+~0;=Z4LvtDg^-zhPPg4BFUtk=6gUEOeX+o0A|lp9Qo?#y=WeO;ZekP4}yIWS|BcXObm zCe{0!)bk3do?4<4-dnCbOQIvy?1YOCiE)sSQcrak9KT~!saw>!0XRPOySE;!NhRZN zCgT?+sQ9%G=J@HdZK~;7heO*u<;MgwOeki%dP^b0r1rYG9$b6#Tx#0@l2@|!&Zltg z<&>yB4iefMSEBYrX2S2LyHtx3Le<@>h3e)Y72|>#3r_jY4;s! zl4UL9j_KiJEh`H7!DF< zp3Cw~)aG7g$X_cegj!FiS!DSjQKFtdp^i7&HYSeCL{=6zq$R>Q3}8uyq->@|Up(Mo zu1xPn5oz(uahA{pCw&KV4H@9P7kZMP;JSQLU9aF&J{GyT4RgPnTV&h|>8&r|SN;26 zQ(U4XByb+n^nQ^bYX))2kRNeV9S*6AkwcS%J=w@Yuw7!ArROf6y?n-UI&nq*q~hY1ay0!HH9;v&^R9W6=LMvnUR86k$&usq5^%e&VLGOX zz%}GJLnEh!MvSc>UkN$9w}M=}uGS1s86u3&lz5DoT4?dg{xHGWf{R)XlQyRefoH2to}PQ3ZG`CWYqUWDW99B1VJfqzYUBwg``S~omt zs89Z%{6p=Hz3t#yC)UXNVV84K&JbL z@Ev1$f2u>2l>+yaSBhH<<(XYhZhrbo6aZs`Lt7M2(*}q7blYFB)p_(Z{zS+VTT(q~ zgrDXvzCNw}H%7o-pltQFvVl(eTkTK#Y#_197fgn@z|7jt6zaH#3AWFMGS^;tW)IA3 zO-vt~;Sh`69hvEqG8|(j=8R4spOI6DJseXUh56|@1!Hpa$7hUoWadtG6y%O6oSdGY z;m9g*jLw*pk)1mMl=Pg@4t56G#Pq_9(e)eya(bF$8FTekcHNBXEy6AKD+Sqchs zK`6|~AD@*Ycp6fTPoLr#lZ8|iW+Gt)nOS2B9iuX#fsCB7Svh0tu(T9r#i9WM_;`9|b8gARs8?Glmsr=8i64%9)r`fLPPBa?(d;XVi1_&&()*Zu6np$+`LC z3LKL&pv0WqLI_llH8w{GmkC8e_`*!+HzyN_oI*UF2@Np@6eV*;aS^O&m2Uqo4o=n>R5F1;~*xeq?_7C~n5g(sMEdX6JEe{6bA)>OQ6pMYXG8tb*KV3#F5j z>(D(fhF0t`Ha~ZAVWwfyi~g@qki|%lCj);rGH{Gn2C~+ENE;MkxDM`-RvxrgpUJ!r zoTcGyp-1Lym>+S%-8j;j*UEuM&&mNZH@m;Pj4E}{JX0<_)8tI%)kfux zMfPOytV97G{jf%*oBp9h)_Z)ewd0V{=5_bEzlf7BWKwW#mLKXJ$MmJu7=+ zzQ@D;->sgE|845=7}rC?#1KWMmu>MIcZLPfN?S=BCI6`5ba#~io#t#Mv7`#_d1dQ8 zrkJ{g`7XC>sW^@7X*)R=pfzij&`efeivszJyVvqE zT~;c*F?n$qJzJ-gUh^fy6~{U>v6-b7kw)=GDE8AGW*ZArg|?_$%E1B-t6QoeSv!nQ zSW~?+d21NmShrN%%p@lCF6YZgu5%50T*4#sJLg91s&=v!h|WxGyL47#zmnOnUhJ_f z7>^F@+XD9MarP*R#$yco_L~)tU)bZ#NId4UZ^LbP3}KIAreS4}o9+j|U$2qJa9)sEAUG}Xh`__oz2D4wUw7}y<_GpUR zvz(3C<5?`|an57Z&g@qQ_Be+2u5$yvEt+XM!PYqjJN%pkXR0~>>4--UY`}DOWsmjj z@iHEZ%DK1SEO)+zr8Ca&u`kAXo;^Ybvj<>@k7q5?B`kxxj3I^k3&qh`i#w9_G=e=gd>xj!`Qc`?AOcys$2}W@VuMPvu-}m zw)s5Q=JOnz&vR=Y&#C!5m*(*tn$L4*9?zNiJXhxN9GS;*GQe5=R03v_w3E%nx4nCJfCZL9@p-C=MhLck85)t*W^5|#d*%7{5w~ZWDH|%madqWuZa%Sh;u#-X_ zdT6Gw>^scRxn(zH=FKg;F*9#&*xOkN;D-GaD<9mjN7lqIZrGQZ*>l5Y*9$uvCgR~> z4{qX3n4K?VkIC%u279b#k8Ec9sWaUrU?uy-O8~ntO_TtZJI=4zV?TTFvcRsn6J>!N z9PV7r9*?ufr|j`QdxYa28s|Ost26t>u1j*xXOD^Ov6DSEu!quymECLX=fF02v}2E_ z*<&tyoMw-Y*h9q`|IWYJum0>;TlSdC9(nBXDtjzvkDu7%6npR@%8n&>PGpaC_F#q8 z$=2pM*~VNaJ5$Cv^IQJT9=yD=qm@M&X6N)dTjG!_XDoY+V2|$X(E}&?IGeJ^^WE`S zz#cg`Y`{5~J#<#g%drP9_3S(vUh17}8@clWdwj|sRk1hLS*q7eJlQ%z>~h6}`vA5} zPWT13a#45#HjwSS#vWg>2lor1Zoj~$4~1VSa{Gn%*e~uD&a+?KEi7lgfx87Z2+7?- z93N&Be&I9bCT22oXSI;C9(%;$u_!QWbc1HJ_YQP~Ptawd;Z-VphR+j6GD5@n<<66I zcKL9d@|_PY!A-mDLrZkie)gd?aMS+sp*3{VO4B{6w=9j^v@jo9V>iv}Lu=xuMf=d2 zx@q-%XwBTTrp0NfLk+#)6n1Yp8+r87!-wY43l_>03+K^Gnh(vR7pD)+qnAP-nny2> z_|QChndd|E=;cWtnny3s7N<4#=w+P`&7+qsJ~WSB-t(ck^-_M{aBQ$&(Y5SD{2$%A zO^GlWYh#a+j`}e1DCtWdnny|JeP|vfUG<@Pl=Pbq&8;Nz&2N z+RpCm!L9^#P9ZpV-pQ_za6ZEx?1BjAd+fnZop7FJ54Kp{d5`^Kvs+FFd!(>OFZN(v z8|MUivugOSr3+CRbRS2P50e5q+!h{3$^|}kt$PF44qN!cpOg+|t)^_cryhC{r{1*G za!tP+zP-E>>Pq}Qd}=uUZYpQlp_U%^H!HF9Tw!>1*ON9&%TQ20jkOF5!r!_LEITUV z@0Bi=6*l~xHQEx!LN1$R=@^W^r)FE?8NTdN%j4|t(q}Cr%HZ#fmn=g{W35>C4VLYA zRbIDrQ}Ehjqh%3ZzuIUyTZ(3FuinL_yk&W~ENz<|9!A$hR*R)K-mh+>m)^GwqF0ZR z3Uqya5GL=ibfp6uYfb6R8sVjA{704)TKTl4A-SN@^u3mP^wAG2akR}2OH<`6O=h@R zwZntx7av%f(X`!`$8ZdI+FnaM4c=vmr7ibZYAS@Phb--se;B%ziEEp^7Kaie&=Grp zerBc;K|k4R2~(m)kSO-2DV=cKGLpXcp~a?jW$08|Z=WR+x7l&FILv&Xv)_Y%%5mPa+Kc?IVj-+0Fyf=!4Jz7xnrfOI77-0XzB;U}=XfI*t8uy+Wrz*)A$u+L=@SS+8y>Ns4{oP< zvEfOiqMb&4Xh|YQnCHvH=qnFf%8*tvNHEZJRlibI=%+_5VWhbX*TfT!C-tN!sVVgB zaxv9uo6AvUu!ptiq$PnaJqjiVj#=uFOc_3dhku&BwjeS>Su9Y`9|NlG2}>2SK%$-i z>S?XBu)2`XELAYI#TiyP0q7&2Sv2yRgsu|;;g;m6la?IisK5>U%uW& zL#AM=AvEesOFQzCopPN(dL#Q&Xs@m@;q>{ZYnCBxW$;y}EVb#`lhv&XE-_`noAcnJ z=(PO`5sj3{gr|qKr1A8vilkAsA|prdg&Sl;e(9sxV_Ws;GR&&LDh%!o0@ zT)@T~F<>cXSmem%cuaI)U>T#7Y&?*U1!hdj&7R1|3&r@QX;RA1SSFj8n#|{$MrCBp zoRm=qBZgVom_TBwPA|Ze5n?nZuEg9^VL`p+&Izz93`;g^``04rxr^3;6?;bBuSC$cW5WXzJLTrX*w|1tN(CmyMrC5cfSEs=yfEeyGT8JR zA5hLHs6*A?D_drw@YEfhpM|pIo`PhPeFYgA;~k^ZC-Rw&dX6p_v&N~%bsU(A%N3T( z%+wf67bEO!0%HP;icjaUNx-c1oKYxq_&%`^htaS}JZbR8Oy5itT3$xj&@~%P$82OS zV#S;XOAkiNz2-PE{*Cc%ccJI=Kp6U-lvRjn#3^#*J=eiz470|dq<|47P)4SY8duz& z>%omcXZ8QT(!_Md{gmcqjIKy{<3)k=(nV`>#hy|3v&aeo%tz-sFz=c_3KPpz-LF_? zW)-r@4a}hN87xf6BDckKoA9haVsh@HvgfXe&CN+; zle62o6AhEE!%QtdhegMID4PqSw|dox_&+k~BmOrhogRO&T1B#7cq&@;vc*DBTPOcv ziKKsgXpNvR1Vz_Ybeg=++Jj#B#*#_C6;*x6Rn+bioll^C$$W>Ny^6Ne*P@npeRta8 z2qZrl&M(%-)C}N)bC&1;I`Ky|=iA)0gfj-WhU$^7=HFZDDWr^pdruno3uFRm*|&OM z8uNo?HL*#`px;5Mg0*%{ZQUq;spz0dSI_|8f7!ByBnnu?p7ners4oKfBMBCJNmm)k z_B)8AlZ=GF7?G5@YI&Tb8Ii>ML^8~X#FqpX=|5Wg3!#lR9v>KCAuk$%8u{=u0)76AX?vLXYnT-yNa0U_*B`f2mK5+opqFh8{MMZ;Ak9Dms7jY_xREeU?evE8MH%CM?Q7X~| zYeY>NS}~%V9u@_$cv`CUDlTofz^$$rF}_|&xUYpX1|yvnqmfRP=5^PrKmz=Ubxo=i z(M(Y~&@GiCTA{<4+*ywa>X|rEXfBDx5u?#g0O4fcU# zL@@)ZsR&h(W>IvO9@2pBo~4(TkP;NeP379F*2w|NezV4cdiMQL$iDafTAQ^KTHEET zHO_R-CTnH|4B7)!kq((;w~-Z5H1Y%MaOE4p@ePsnZ<({6aU{FE5`?@DyIkEtUq}pz zFcQUKM!~4}k7cl;G~YfyqMxEXM7JIS3+!LIt3~=AfOqEMtSJ(XJ$-IeMCa zB?iPgKc`UvkqJs!dhBy+Rk~(=v`XVsYQ}|KK)^+1@-xO1PMMIg-1$8{SI%x%F4OS= z5pi~Z9%1Aap{|Fj(X}D=XekIiTU4zTy?V1+S=#$UYmmDF(C%8E#adekky5ees4K+_ zV8d#>HtL`@1oyE%+<{}YGj3|h`@>?PA^WTy=%uTcaC&UJ)`C8VSB0{`o#~dl zQKgmgG=9Ie23cN>_rP6~_FJ0=;^GegvfUqBAGSs?EADs1+DUnru0CQ-RNiM0kuTifGis6F49jFLQ5omEIlTw4DI$z)IX+**sy_`+I75u#K3DHz%x z)#$ORHLNmf>ey;aq-!ojh70O>WZ=%oinPrs>qxG@i;lqs*7BC=UeN%KxGh3I*+jU$XY@4=y~f#Z01Cu zRQlNkYXl?kHc*R;)|ZuOg7EbBAUs^18GU!kUnW);X8yzX*24;BfLQRLAAnjaQRDEU zOmxlq!Kx}anU@2uTn1pB1a$wA0chHfR;OFSpMJFVAh_BNXd9i?Ib5ZquUg}kkJ*P_ z^z0oih+ex29v?#UtXi*p&H9}I=ULwCI;cj{9=mRx3wvAkjaHRbyJ4+?`?I>-u+~z3 zV(dIdM}9zBj-rO=R`)AjV0G5Z%)tb+EVbJ59R>we`LY7zo^oAHHpE%wcG$q|nUY zK#GVKdS@@FsU)9|9GE+jHbAuh?MW*J+m zvQzMRryS5Aa6U>|+u!Vk^Wl_jhExm&so)0(a5Z9$d($A>I&vv`g=+6fbI)ihZ5?b2 zLXLF}wk-+26Ak~s>-gXB3vH#lG&#gJ@P6NeO?didi0u^;gR>Zq*-|h@zctj>uB@X5 z=Ypa)#uiJfm$!8yttFyGF~qXL)#7O53bq<#Kn;5QFAe)U!GSmcw_BPJdky+(s4XeD zDmY3BDJ}}BrJ%E7wN+JQ6hDR8nvhvFgnji^ZC%I{HE8-hYYM%oLKmRS4$~{MzsU`1 zCMh$75K|2?lk}Q#^klg039?>_`EoG?Pe@FJZ6(<$5%Atj(5XVuaJyT;$%3o5fR`%T znvw6MfITYNdXVp>fVV0^Kv1}V_{#-qE&1@`sf0jc8kI@{g3TV+}|M z3YYK?A>pqw`k%cdjIC+w&kVbkturm!Wl@P1BQn_=)+NT44ZV3_4FnAB6{gD&vnldY z6f)6moWDiWTg$`a>Bg>(vNSBtRyO3eyX;?p$6yt2vpCy$R*&%NwXvvPZ&Z%P^j$66 zTx9}_xTn&Wo~eaGJ3dBKuQh7h(gLy9i3@e}N%)uV>Lb|(*%EJC5}+(Hk?%GTWM19A z)zH>~1}zN_rTCSstTEw+HG)rkj?QXo>p^$oH(4DcD&LUCwy9_`c_KX17|3k`*|v!Z zxul704(5zJ$Z<`9{Fourl-2ZHQ=5|s%Ev{ro7n;sG^GLN4fVy%ZQY>PFPqyME4SHK zQ`LDBlDMnRdw48W#N+2{$5M5y z&F*o#N+4Y3khZqEWCYIZWxjtX-Q5Yke~^f=I#ox)vkyqJH6W8DqM#Upd$s=UY>mlc ziC9n!p}b{_qbcoe?a9j$v6dsykh>M4RitZbhgUb*`@mQ>@!2HYQ(MUNPZG6-*(diU zMV0bhgbXo0Ewa;_=#|lH-EHNKkS&dn$9vdX8y|6uy@=!cp0;@7 z<4EJ zCytvKla$_kEhL`W``Jo+0pB!O-0g=ZkD0}OgAy^o*3qD#x!;P+j^myUcc8fQ(NqWQ z6Wa00F6Aa;CLQB75xndbAzXFJ4P{D-EeX2_qcV`VV=;&&u$J(jZWzm2*W; z9LJSVQ~XYQ$2OE68;y36ofZwYC3<0+`C?WLv9jl_^#+X9>2P5a&m(XbG$IzZe)tQA6#yR{xD zCvfk=vUQQEIFye!H-qZPjNk=s;UrrUiK!#x#Ux)-@NJJ#%es*{Gfy*3d8P$m6yPZ0PO@ zWEajgV`yHcixwcydeO({!FNh>mM^(zK3s<+PxmE1v%przATRYLKex~m`bA&ztBc@D zIdhD0u}Y-7-xR#O*mf1|FP?%=igVdV$1H{ClH@bKppPylK6U}jMc?DY}V_mRnMHY z*O%M6k0>g#|)>ND4Gn$*D1!=H&>wu8DAF}Uw1u? zrk?Tj1^zX3xR8RYqcY81i3aPZr$fq?73wg+ZyGEPJ!7jKvEm^)34v`VZk*fnhZK|E zwf0#yrgBnBep;|PNtZnj*J^ydVSIh=1$4XQS3>I3q}8@r%1OF)4V7+xnt0+=?!H9gX4U_09Pd^)gC&ibV7;hEQIy z-KKw9^>QSqzHo_?>I*|!vk65nhkm;b$uMa1y=m9iqXIH$&wA7Tc-5BRrfv47{qvfw zmYcS>7;OXGEO;_~&_;aRjgEnrySZi4HJeeU-=EQjWo=UE6I52IXll z%7M4x4`rB*UX+hqwm5@=ivguh7`KD(zzfPSC%h;}-bGS4MS7ZPeg*yLJ=-DlWx1e# znHb!rV|PGMNvS|@9S|8Y2A^_1u+=sw)x0RVJ5eFXFpaz@Q+C;!3yKuymJo+@i~ra1 z#D)z|??(7E!IJ09umq7agR#}i(-=Iz2e8Q|SfO9o<-NA+$`S_a%TCo`Y3sA!HU^(I z?nA93DX)1^T>H^jmXsY{l-&oA36k=u7v;b~=ulG5dr^*jWQ39WSXf-pwTEn{G0}4T zFofg%k`VTLc4#1Wv?0N=+BtU!)y~;_Xt>V$7(FpFK9b`}U?Ls%3A!(4QlgtQ<_OHh zOzP++WgmrzlEiCRC6TL~3{H6PEStdC$$r{+5x%Tbq(F`petgW<1xu?vusMEVXO7$U zDbF*QRL451oJ7U-Je~3xjLuAX*PuLh5{WZYJ~1fsJ}*W&V^9`A?{V-1$n6mkX^a+Yx3? z?Kl#F+nh#{%@myFj5zSA>$fNXlEQ^lF++w%0&yljP^NAC4#}TI&z-TQk{Kds*{MP@ znO`rTK@)}w#B#rgjc09NDQ_@|WLCY6E4d)u8+6Ed$Ze(^GAJ1rY<0aTrwvNxMO!^D z$_;~({XI&TnH!-AR}d#}qV_qDdh!igaLE&z>*IC5B9H&UwjJ{o2+sN?#kfS%KQ6=L zNpc%s@|_FCh*#+3$ z>T!+3t|Q-Yp%T*&hrR3^s>cMDa)PP@YS3w75Bd16y5z5 zd5dGh0=2%FwJ64=A)Wg>T!AF__9ZX)10qWDNMG{2JJ5$DPb@|z4I8mmPbIqMu1yCB zQA{()gg!jEP`u%fj#2!ELgkwj~35GvrTByBd{YU9KO<0Dpy(!J;+A< zWAITSI5(20n9#a3vVx^F0(!Lbaq$G8-Cvu29uvBiroL}0Pt`J7T_uHalm2Cdh%SXj zl!XjtO1?p_Swy(un6=uxEN@ zpJ(tg*fYgaTYOF1Z`0|fu8s=9o*5P^BQ-6Pj?w;f9A}|~YEkszZ!DITccRMD>`*O2 z8Bb@2YL6(NGlAqnhCJGy}U5XQ*0)pyrnMo zvCXO-6-HkO*V@s@kL?NcZYRxNF?LbF#Qdz~&fXX#mg`KMztO9`99B(jf=`|Whip+_ zx93JE%uD@Fi^8?%Fom055!o8wMeBeIn;@8qbN<*o)EgG9sggkR>PA(hH@ax0LRdJ_ zXFSoEM#*I%;j~eNHUh1E&Sgu4mTahMz-SnA7xw*8rMDzswYH)yD?!m+XmTa3I_c7c zG1BOeNUc5n90UT^d`_xWWo?_1ErK~3*;>(VRS+zTp3|@i=XLgbjB9rlt&XBR#z5N2 z8{rjb6{}WXSt#Qw2yZ|)$79*X8Y|F`u?QpRA*&WHLclSwg*q#2AfozZY}s!zriqx~ zx?t0a*lB-EIb48GG$3DN$TSAxv-?~qX&Og#t&4Ji1*k)d5~BlYC%ZOAIU=QDDK8ZX z4hKZa4|r0Z;!bpFhnA^aF~xbO7DB+Fm~`wnxhSQZ6s3(;6goQ^Gxp1?0d!A**l!8K zHokYl!|Al4T0NzTKsu{~TCu6n@QLc$8|<==Xf2zav7CS?n%4lmW>cYnc{Q|oN_(o- z1ih`GAFgSlSBcT4D>(d)iEu3jBBTgVuUHf4*;s_m6QI3u0AcqMi;4YaF+q!MvCnSp z668%?mOx0Cl&5v4OJr)fnzwtJULt2M_z|a?z!T3@gnAm7q!)N!zq8z7QXK# z9%TgmwypM-;GXR+oXPF9t5~1v(c$myA>@}*9sK2Usl$#Pw0)Si_CP=E2jlcRfUPV%sX&Fcf$LAyBlYew%4)(T0YM14F2g!=UC5G@V#q@h|S=_*NN7)YIH-dGJAa)(FO zqFKYVA~H-;-x?0~gC%?ZlEPoGqOm#}nbNb{M*!8Sg-HEO_ENEhNc|P|0>SxWm&szW zOM^76lW2)Gr`yuBE@W{FzV}vnigr&&Q*41NFI^i*$TLy~$7o2nfZ}5$?LS&;Ltbkk z%yRc=z_uVJW|p}bhzS&r2Jzz7Anuxs8m(Cvo3UtH@tQMljP@isA|n|(7Lgog)DOrx z`R#HhSbirH&tBjjxNaL~Y5mC`64k*8)UOi7UJTTePHhpX&{E{nm*ap6X({rFzkI`0 zbDdIUp_}$LOMyxz+6z;%Lw>OTP$;6 zTZul;)uQR9G4S~Kl|Y8c03#+Kz+f3*H(t;R*fX28Y)v^^I}hLMv+q6VBKG?r)4&BX zOEUR3A53OQCant$Kr_0i09HgL>Wf04mP-_S5p0^#jEP!9AsT)qkvAm%pNYV~F7auT zJoq;zX*~R z6pz{9#ceip#8kn_Z8RTEMXM@+s`Is8D}S&C(NCu#{6m2y@m5v@e7*Pj8X+Dc@~j2Y-E))Ub9omw!>e+1Cl5}Nmj3A*bMZMf3W6XmIyAhwf8 z{$en#F-seXg+fd?x@9kzwwn#6gCsO*wqR=ZTN~Loh|m32=%aY~n_G=^wnHD)p2SLi zcWOI72E=rk+Rcw?Z==k*i96?jSR^BhoQs#mGO^?5YA12%F_)|8am`NFOVpo_3zS); zF;9p%xJWEQRK@kwnGoGM3+d6fvW(^3;>R-=u7N1&EG1Hx|-b>kVWyt<;c zoFEk~CL>U*XSJc&F%`8Qx!mtL1PW~_e@QxLswdnMKgof9p&(g4UC>u}Hyme^6qJmuy<9|zv_Vs!&;G||W_El)*2oFndyoz`aOHiNJ z3=j@%VVzl|c@E|*c{WVn03s$EH)zjbD+~X0>2(DDRR(4+Y!A^oG(@!>{vJatWH$uRlY0@Tbnt~<5AakcZ=?(Cy-d5x=fBCtMR}S-t&b1La+-@__ zPjkQkx(P2r%MRE1&00|)E+}{N{dgOY3tEWQ&eN>5GX!N4D_|W8uDW6SXqIi))?t4l zLWtofvPY*wW2#%}jH7xGb}2@^r#oDqyseE=lqn1)vv24-Xv@!LAF}cN*bc1Ctne-b zF=P6?3(Qj-L#DK)$!(&d4LTnQ$$k$3GF`LZ(+U-oPY?5IJG8bqVh0~m>HFCFqHJ{` z25ha7ARfB;P9*IOsj_GAqP*_fvQxu_WnYMk#I>! zJpeA5Z7Fsh%fWy>2eifn#|iQ7O!Psm1F4%N8UX!20u~g$bFU`ta}-+O->N4G|GVQO zZ5`<@Ilq4hQFfun4#BQEx)Kg+Hie8d#Q6lAMkEQVD$QOxA`a#+^VkdcafiW}V?hzZ zN~4cDq9u~KQnpz~w3cL%l;GT3j0)>LpI2$uYC&OdKq=EV~F5o z7C|%m>@jT>*&|Vlj{~(+qOP--m!*J%PT&Qcxq$Dn7YC>Ct;vmP+t0Y7leX#(e%^;` z%4gbiLVlEddwt<1yB_;O%MQS`Z#Tb!sS10hGrrb-Q%cdOGomk#O;fC}9{UF4Gb;P) z8C)fy?Mxkc8(u_5{@Q7+itNaTe09?3?v`rD+!rdUZ?%sle>Uis9G=;>*yyTxz4ylN zPyo=mI-_NkZPJd9`QLwmcNYP;TYTa71AR9w@b1#C*aB}XYKWt+p2PU^bS6qq8up1L zm`rI$Z~daRD+7(~yEz|60v3D%(eF=l3R~TREvG!fkoXRZ`(Uu*k$)5NDR&}MF*ocF_ zY$Fc&0S8#J1y>in670OJy$Z`nzM`d)^6mX0zWWi)EiA@nh#Gzo+E3acr42*KDUHtT zcV{~5Dr&|y^!=-tqcD>Pdyzl6hT2Y&`6Opc5ec~{^kiBzcut6JUQ8WJ8{dHEpDSYL zBVapkXhm2I4iRMiyZ$EBF}J-?2mW$(JSvkiv%PsLYQZh-XN*+y#J=Vi(d8Gd7xpT0 z#BRTck+)Ird@TgxYadV|m^#?(U+`IXiTav;_bX-v%s`Y4zrd@%VMI;>xr$Cn70qm4 zdoao6$k62)lVt3&Qr%KksSX8I7;d>hm5} zXfY88b}JWKujVg(D{}RLIM*uM^Os_)XI|{R}+fkJ9S{==q z>j=`fV9o(SQ%Qfnh-ZWK!I*I1h;e=qdqebPD2H4gZuX1WZ;@_lFOMeITpCwiZ)#w; zAwMcuky;%eB%|qq3VLlcpLiU+te>x-$1A(o2btz^VMy~kBF*o}G;f#kzUh_bUaI~c zyZMWy`Ltie$#8uPhTS;g7r%(o5&9GyMVS|+Ycy;WX0a=>-*OR0w~9z}C>>ByZ!Iul z{v3Bi9oO}Cx-1mA|5`#A5#UU-L{i3ZT#h?jm|hC zDcii0Ih%v3>KoXNzf457ib5If4>ilG&%xq54{Dk})G?dB6gPcwxptqhH4%8edZm_* zgs-5DAb>!~gg+?~-n>)s`tO{q5j``{sKbrTePO13eNEblLHEDxdL{JIERlLQG<;ZF z$@NI2zFWaq1O$qrX;FHZ_7Z?@+D@vH7Irx$2ylS09r+U8D7> zm=nC!0-EAPtpA>**C~ z<=Xm85hRt~sO@Iuims!tQ!v}>;q_Zxc#gc{ycX3%m@LL?q(GJ1evL}dEi zlBg$x$P*FLP*=TxZAaM~Vt~RgkZkKLy3w=FVBE1yL%lotLvAFax+R-wj}D@n8^JEO z3h`cPB*f#I4{OZR$?d3PV?C7MSdqNGdL25mDNML5`wbr(ueYMsW(f9B7v7b3wQr`s z#EwGYP)iHFo?`V6jiCEl=ye2AT4L9hJW9ul$m~a2>bWGb3p+t*toCzPB4?O_Q{ zqhtv=&;_+ZmPr$NrsTEm22EsfO+?VlZu$g)l*vozu1ENG4OA-54|3t$q8d0~z$|+# z{ksRUXOTGpq2}|7qUi2kdZj92ENOn1V!aNxZcHa5(W^c66Ie#KtCyZwW(7MxXC;`d zj&4sUtak*{dp)p1{q-)a6O=$_ZPr67y=Xckhr#(d0=hxqIB+M_eBh3dT`tU@kA)oG2MOhB<;6ilBupSBLpeq)3LIJ8n|LLd4virc@cI$=Q&|j}&AaC>svK&>@QGtdv(}SoNa`gZ-DR{&( zUpo!-pRZEu+%Pu{)Her`n64(nj16gr>rjL~qr0+RdriMbQpF9`brK~3o`aT>YfAlK z*pNXC7alfD{|h4o5FX;qv#Ye(aJ>hXzs3e^)F*~6 zl4(|&z8(!61kEPnxCGtl;dBP*DtuU#k!UZ>HAVK%NL1{LO_8k}g~-qo8Kc*A16e%m zJ9$*{f~NswJe!UM&(|eS{$lWae5}5mjmf)}!kyR| z6VLrw2zv_2GW<6Ga8fekFM?SMTFI$Dq5Q?drqYyg2zI9{J(m^PgQkwtElf4AWI1s0 zEy(_gyxBB5Wb3X#V(;c<8Y71orh$X`?rR!(`7n(t65#e<=bnjn&{<79{)@q+dAK&` z>tEv76x?IVro_({mM9;@jHR6?>PJXFFY)NKNqP|JQ-WmYCPA{E#U<-KS!V~SF=7c? z;j!MGtp84?dc_*@8)KtAUS?d)wT|5m5 ze!hfQ?X$r68FnR#d7r;O5A2#gUB9R(yJ`9(#a(dNDY)Pz)8K+X==N_e_&pZh*BPtMYDJY@x=J4YE4>lHJz>ZRLHO1YP$L;)bz8Lnu^s| zd*-|As~bMra=}-&W+!g#o^Pn;M_D^$_(zcmWuE^Cw<#nWb8s5fVI z3B!2TB~LBXgB4Q0JH3@^A3&OPr?W@eaq9PCco{TOSL+dU@?w2A1E5=)LW`DwAe#gG zm!S91n@(7&v(ZM3ZTEA<7r|+gv64&tlK_umTq?Q-KdBE@$SBFC!g5g3cw*>;7ql95 z0zQyo-Ek|Kt*LA0a_q6m3n=J%#&Ptt^x)A6)F*2-oOVpm%moQ zRgtZd%V{J<+2jJ3wo1f`o5gqPZIUc+KMU9f6HE4ivE=Q-5zm1t`xncf( zUqYQCJ46HEGqCJiI`{N_6^6d)2^LCr&J+8}+pCF8)Je ze3Dfnw8bX9TWCkGg}F<2*{y8*=O#Tp#B;pk5WzkWD|30!SQ<9VZljam&^waJrl`xY zs7=j6UhsG#3wwBcQf0r*LKz3$5E0eV+aEC{kS;xhyYc6bIG~OMcv?9L*`8JogD9CU z^hi1oWgSi5ZnSWC$LS6BA)Bo0A;#phw&^Q#EH{X?Aa=aXjMH`eZT&n^ zzGPrAVHffq|Bh~GX$5O9-QQ=u&yAUPk1xNkf2?4jo{7cBVb1Q*JE6aPZa+ToL5Z0k zpd8(m0>1Wv{;~n*^H7mj(H+~e6V~)Qx2EnGD>lB|hU!_LalkJ9l!CSRr!cm{2R;Vv z)`w$tttXDKJ&2=PPoae7dk{x8Mop!w_JR=EQ_K$W7s=FhX|G;J!F;fXt92jrl5FDI z>;M9HlU()v`iFpnYc}aD8LnmkFocU>D~fI%Knq$riRK6OsRYBBT*hOE(65zE_;!c& z3T)k_C*DUs#@NL|Q@r($fbC;4UOwY!hA;XA@aOIaA9O_T3+_Defk(jyty;be?4Xzm z?RgY_dY1^@r%8AsxuDYypX$+MM^7AjWW%wqx1-9?4WH`mvAlx|&rrD9q~$Sm)UfV) zh27zL^qBrpDV#LQ>3mS+jlYp;o4!Crb%ZXfZ+FlyztBHYuJTl3W&g~w_6|O$F#d)Z zpSCAqnwj&FD@)nwpyW0Z&rSw*#D+WQn$udj5{_h4F0Tx-#~brhvGJv(Q@tt`_|jJx zHoMB=NTq`VY6Q^{U&Gpt^fb*=?)+LmgeCjRX~T%OeS_Wu&XPEd%&y)`nAKya^%o2f zH{EI9q8K=6(YN{!=u7}BO3ktF@VO&hb{3;LSH4FMwCg3zc;*?{

XO`dI*R_4-+i z5gC};=k&*wNdj|Tw<`sL&$#n|wxhGo>+hnU;g0H;3;4W1K-h0Lo5wEdjp(F{dT-1~ zy3uwBqpTI^nNl!bxp65SkdiGC?|um=-IaDpudZOh7(&Z}z2yh!s7slIM^`=X9tOi%J^#-1l-5Z5v7B#A$M;}(Z*{IRk9Zw6E0qZ z;3DsnY4__GxWpM1cZ?*Kxq-sdfPF}%zu!b6a9G9f=r5kWp{E-_oalM6G;V(5I z4D(eTZ=vnc-^BCIExn~OMDSelGkEqFJm2|Q&oF?T=c!-7Gg&O&#`#+{gv0o1FGocZ+=uS@*lsBUAHuit%=!lgqSL(6IA4;T z<+>u*9>hRwx%Y}9dt=i=?@}Rc-JS>bg*83$eAh~feQ+tZwXU>1+c5ikrR`X1f~nrp zIHVb7@7F!{=p)=?F9s7ufcwU7eS~jJ*;%8x|3hlc9#JRlfM@gdql4`ErZ{g0*_*1x zPixMlt%8xPykb#~mr?#x>)+jRAUkK3t{oX;Eo(ksl?^zq!9=%|K$J#%sNGW<=Z4x} zQ=Vlpr_#&iL3p~4C|~?#Wgk(#8dtEd!kNGvH7^XPEfU3F4Ad84_BCu>G2`{A3e-V~ ziVw$&fqEp|z8Y(tIO>E2gzqGZzX0ViF(!jiwJnaY@5Sm!9_-bM2xj<`3YF}e*$jG3 zyQm2su8ctC>Dp@c9+dwMrfch9tIL7P_Mh22I&d^>aAYtosA{(;H3TrfDmVrwo8sm{ zMYZaxYqjI(ZOjxJah$ce1(1twx@z{xSopL@vuCo7R!yiN#STzvvao}Vy1lQU%aJ@z z9gr;6-R!d4AH|f9oB!%aq+yy6?N9dmVUdQe4*LX5>2TaNdoV4GLK2=7xPmATZch}f z4%6s{yo;)V_8P;b8LV1Vw?EG2(YZRJap?DM!Dd=CXHyhycM^!lYbPcvj%kD%xVtarXC6@dK1i9FqQZEe}1mwtWLz+QOLBu7mGQXxlnSo(%qV z9s5c&EA#3icrO{eRz1X3x-ZM*0U}~Z#1q&p29&<$?4MpAERVR*s>)}}(|9yP6YLS; zJ|0hWj$na&@U?$a`<&9Q&Q0yll_rb(di5E*w}Bs9z-942`nt7^T_;aSfV1u`00^vu!qt+@l@DM>nM%G;IJ`r(;ZeBorlwFX2Ag-o6co z+VHe}(*XgF)0-Wj!lNt)KE`HHPWhq}f?Sp=WG{l=j7E31e?dq;F}k;{3sC<^6n{A? z6&=}?X_B{3UH!YFyGS${=3uvf*Jr)%_MT-(d_S`$Lq>jLG&k$^W0vDzop}{&Sm=;` zP#LtIbmFZ=-bHOtlZhF3wpaVc0JWf>s~y#}~!1zkF09aj<{2nMTa$>cRFls(5y>1{AtBjVqMXq_tVo?STrp3TtCSM!e^Ko9Q*1 zedDz=o9=W2_*7?Unm5`6VEsThp!;g9o~Yst_+_-+&Hy}ToEiU~Gbb|aElA`3W_zYv z#v^AM^uNC;7v&;n;`={H&WsvsKTwJcz?o3F_DXc|aJ$WW>Wz=F@Cf_%_vDWMF_zvQ zE>%4faNfDaL?b<fd1E)pnv6I=>O$^ z(Z4Ib5N??qLRX^@s&6~lUbT49C@O&X2mV#>A9`36AKQW;WOoVLW|ESZy|j(Ok^3+& z96T9*Dln-ZUV+)B*!K`}&r3le=L5^g{{5dNXlc(HINY-{?SXXnbbIOWKYaD&8HZG6 z*c}S?59Q6W%emo!J;dBF3^ds0jxS<>kI{Q_lMhJ_EX_L;-9%?1ZUB8_listkvjAh6 zvMKBtn5@a-t4d6xl4(kkNd{wnn#mCCmZ9|kPeJkT#spuQJKNseyL5P~ghUJw#lT-V zDF*$+D-YRqH)+X%k#xtSs6oT1H`pjU6(6%VRmg+^qDmh6GKO8Y%znK3BS#^ zH&Dnf$)EXCau7H+!*O9D0)fI}afL3jV-f^!oF6Ccko@?I!OyY8?o`NS$&a~Ta#Ql_ zQUrdWfS<*cSA-@gd*l4dGx@%k{Bqd~`0+L$6V}jGg{SNn6%sK}=&HvGMsZ=Btw#W< zhSMr>g_aya^XabDp^m5R?MS_W>{6`;n0VkF#99MI2Qf0G<^yyPEwpI0JqY8a$#2;! zy0)ygPbKu%S8U-dZk~um&vAj)K4+g4K>A53C#*$ckePgFu`FG;);`odg4pUsdp9y} zpx9j+O}}^%ZI#S{;wW_^@fy(Hln|`+3r%vC3n_*w$EfYp{s3u9O!*(|y?1z2 zRTD7o-q3d`sX$2f-n+Xgl!PQ8y@lRFRX}MOl!oqK8HrUq&DJ_&z0BX+=cB3s;ONkQR?doqADo{Hflnxoyog2q2=n0@OllxX-myPAZwZ3XSvvz-h zjjLRE7yQRr!=`fEh<$p~*;trj;P%Eq(L)#=Ia{pF-oNFHG;zCt{dUWl1V%u)ou_j9 zaZ%aBG^_R(n5lZQLD^#?|8gGZb>r~x>>W+Zd+s<}2MF(=mK(9Ce}M1ZD&I~)gk5>~ z$^_>d{;CSDc;ES$iREJ~>ptugp3t#;L}j_%gK`zjKa$pZcFmT$54^FzAAokDR^E|! zgp0jxDw7S_GMktrTrY!3-qowL1pfj%^62Pmvp43}tQGG2Qn_&pyTVZRz92RdDh<_5 ziiDwxZR7-q<=KYn@WIU|78Mj1WsED%o@f}RQ4rXIu2n%i$VI>wh^r|2d%&2A;!Qzl zI8?For>cn2Lefyh&Z|`iFo;zj1|wlyRk1aPQd{Afs$ySLD|BT)Ruxl(?s{1|tFr8< zR<11YMHZ)BZ0$3j9J^S}SNC&v@r0kl`3~T4yak6%tBWlOhezE}wb_R1ViOaa)7g*J z#qPpPJ)2WiHn-Mz7@Ku#iab6!{|+G2*bMPLSrcM^a}H3)0aY~}X9S8lg0KN~+=vB) zh>e9eR0-yX0N4ga$2&sA+8j#NF?b9i6dNLk$a@8s#(PVbm?a3UhAI8vxJPUubR4GigVZPhgD6NbVhEcT1^ob^ zRNlXj5<8iAAH1mbm8gT#tUs~gg^EoJoQW+l?C-yNh{sQ|bPV6nbsArrh zN?#WLFtfTBFShb^jGm35|Eg8jcn=~+`51h&u^2DxDu+S63&n2ydV)naKFWSefNp$T z&+O-%*}80JB19=FTh-ufq$I5uYs`jv=Ou}gZJb-w@zADR$I2{XQB!ePCE+G2x)H0> z8hY_RsvPTD1K3TXXn;}`{a0&ofJxDTY*-typAFvncNJmTphPLd<#5g6-1FCAjoOwg zfHEtX`%cZK>_}VD_iaymSHH0!Gojup?L;wv^NiBWN!FyyTrQx=b9;(Ws(m_0^~06TkdJ$chXObkeZ*{ElRNv0pWsK+ zKuOAFuAqTpKFpPo3%oG)^+3?+0(N~M&|cuvW|POnIFksQ*u=-cb3z;xW23*OiV*pD zxgylV^_C;GU~GOt=CpME>TdnxVx+J@mF0`a#k&G$rw=@OjeY_qQZ-;A#lN>Y>IiW(=o2bv#qNy|<6-miVmh$ZDishyAhw`d!GB=5$Aapk zp&)jILN=HG6NUe%WY0kk1lvx{7hCfcUuC|aar)%*=B0|^HuwrHQo1w-kU?^&qQAGt zSdj^EqX|l~h2bjsRpWrz6D&DPY~lTBoH$>A>r9AxI1>sA*@aAC{s}LXHy7Y86BZ@q z0M&Ua0sfCdprv$RhK*)njWLXE|@G<6RwX?c1hlzEH2l&oU_Br9 zct$LTSp4k39PpH%&K9e~H7F!XJ!#{SiYFa3r`%2jeqsL{kuO^=&Ve2jGg9#e!E?o9 zg2Ih@@u2lnoL6tZr^N7za3etz;=@wK%5X6{jom2~55gxJu^ewBu4In+B7CQDBDO9xF94T|<0fB%3)_im|<@5TF7xRbX-9 z!vtQGCi!llIlBJtoBu6B(L>l53q`NOg(~^?i$L;O4A>LBwHJ%Q0dVI*6aQb!{H07> z=&b17vrN3pgI=p*oLV7vhI_hoSAy7I>A1#?r7uSk6Tb}qfQc)kTf$>8A=;W3{96di zV`5d|sLJO;CazPeQTcrKc`+nt7B>-k4ol;DeEGbXAq0%_f5(xnc|ojJ<&jbN*!ZUQ z2}k(yV;?qWl~{#*e>YHpy33*duNIP!Ac3O{Awe*VNBn9rPUs7FGmpbJAA7Tl>%@*# zdMMnf;XqNL z`&XcGe^DW>7$Lg3>a(I(`N{>}UBg1{ff0az@MOYkqK7*u4iLurzXgi**MX`ZzEMns z&;$q&hX7!KTrLvrN z;306`o_z|x6wfYsE4(k(u-U#)7{Jka!hZDZH|~jWt$n|kDqKv(w?HiG04(m{Ge`Ge zKv;f26db~hR5n+TGVR0tqX~`|5^Ho+{0+u3yefSszLuS}J0{i1d zyZN+O#Ri{ALT>wI!NusyUqZFBdBzYn;|xGT;TbW<2ZItdJPQ&nF~Wqh3uncVen4Io zJLjuP^d3GZzG;Jdi&zzsIruew2pw>H8n%+&xP)`tk1mPN!G+27KfuEqxHcUj1ddgv zwO@P>zCMwE{2&}AXVPU@Ai*vWz-6mlhQrmiTq3|CS%6srS7(48*BiM#N0PLs=hW`MVc8J57P(%>D!~YbI*dSU7;NfDY{{YyP z9eGo%Yg!%OW+gYlJnwK&a{hS}<|uqWr1`CfO={QQf?2b=ExY?KSf2c*s{IBp&{*ix zM5@g?-WKbbSO{mix5We@B8~1j3U$&H4#dC8YZxJBLAfn2q$L9bZbX+raYx z(ITHgh6YHRh4ny>ze|s(Ao02rD@bQ-Td;2X9;5ePQ&E~Kyst9AU77HS%D}Nofc?HA z(w$0@$f1yhiItHo^8Z?8X{GR88k@KXp17>6A_Xh5O5Q_Nq++hg4%H;Jw}{@8)ufgI z!ar%gjklTy!PGj`kit!CsLJUqyM`1G;Ug}(B;EEK#Jsxb1|?rekSnr?no@a(FCwnP zYh`DS&nQZtl$t%NFuh<>dVzjXZa?H#2}CHaDMfJxQO@?Yd~%B3!dg;Q0U|vEI}xm3 zQe-XmdXSU^A5BL7Fo4VK5Gh26Pgfkt$Y80h4xG0wc$PB2Uk?F)N2&i3B6Wt(c9a3W zJydF@fUE1Ol2BxoyD9IaFlmKNC`iY9n5;(~sflVF-k0h~FWO*Xi$ZLD))mCYhfD2j zrKFns;UL6ZRfyPnQhy&f%KTbA;OfP)!0~YuQdhY;6QObCh?EAx9U3;;>9YsP`==9L zQ^6>P{9px%5;Xc@Qo*|t@bjU{4~Fnj!E4D<8`!$i6r_VZCWAgT$Uqk4k{a56FAIFX zOOjM@m8`SzkpK{{!yksqdihRpJ!X-k*aZ)F?1{P zpsIs&Smxq)@l&o~mJuc82=U|mi{GGc{kGX~oN)!58Z8YXi{Ca1z+GdE%l|5$ENI(| zGc0KF!=1xprDj6@IOPMoIpdT_Z&^x}ZiYcAN7a{_2+yh@PZ>clQs$@zQhi~K3i6@_ zNGyxp5S=9KP(ijUAVL=Wua9dvew;C`r7EY@(v&&kqz=NjD$%dide8c}M*-`^OaB&b zj$?B#%R``%F`lI!;`zoBgZqgWTS-IU#x}flt#i;DnB}8U2h|G6snH5s;og1$ql9mBVm$h5FEmmG?5axcW5P%ad^;p zwym2~mvw4du2bZr;F=~4L3dbLknr_v!~*ZwWTIg|rRE9RSM~cB?Ah&Hq(Z z3_A;c6%TI(D&CDMuCyB}D;&eNw2;EtYfsjy!M3!L5+MvVCsctKvbnSCwS?O$mgqnw zwv9AYs0i^V_^r;b+ko%dtu)cQmVCb2R*Hir`l7AW#?(ZyOll{!5*ol8ZS5i@#ID}j z4Ve3;-9sBFuAL+q8iAgc0+$w`JXya^3 zhKWOw3Nq0W#MMb+!Xi~aSGzzDn4f_?fd9qs)347^LT^^@0=z=zqC}}~rTI_~w9DvD zAbO8ZQgt?}it63POt6LT-)WH z=Bm?!)a>lkY<^NRFefj&cM7>D*T1_IDV$JMepFTYV9=4?7oAqUleXFiA8Hk2u;Dmm z*>b*zR2L?Lw|ht_zIj`EPw5uiyG%}za1uVXm(&R!@a^p-HHIDT)G=y5$05j_Nrs?A z_(vInzUwXdzmild1@vDpQyGGgYW71GVpme6+ts_$g&11|i?7I(OxUY6e97oK3`%f$ z=C+G{l_D{=tFN>SR@uNLz2EnCKVTsxQxW)RKbSY*I!*aV9gFJ^{dN|E6 zm)E^oSPHQc;jR>6n4ch+7(U5njFn>H{hFTP<0`|^Y2`Ak-;Hq)=2U|~bq!%ZkAWTx z>s5XzBJ6gufSoUtMI0^I*^6t#r_H4m*%8O@&XToX7|Nivb?aIN2}nMTN5m zadI^XD5%^7JT^|cW`h+wg5lOw{^xK4MwejJe36;xU$q6i~Juk zOIa9)PLP_hp{pR&F8t~QpC{Fjg0cawrHX|A021DTpUF#9hS>IOX)D~*)bMuaV5#>+ z4tNtG4S0f>Ic#{I!XRE}d^S(&VY3x+qyg}n9dSYAICh~OEH(ygsRduWJ?N~(UY!V} zin5fM{;`SD0tH8%=3yzYA#Z@g+@A}iEy4<=vWVr|tEg{H9?3EsfzYRDvEGqI(kC|I z%`Dwhss)pP)lDe4^{c>DlfhlRssi|5kBy!z@sM3us3=GBo|`N|c*)O+c1}-KbcYSq zcA7LAPMS5{WzB-p^QzAApRd%0dUd+A6HXriR9zNDJmG8rJNJl-%Od+sFr(W{nkhvo zfU26-K)&!FmF5Hf575MR#0t0q`Q7}rv!ogUf_s9pqOJ5KOrgtG9zOHQc~W{#5SmY* z%CmnEQ&m-cQ`UbSoX$1G*L4mW29o7J11=Qq3iER9LFM%QwfxVyIE3HCHa{b66ox=O z%8QD^XQ88yVedXGB?xH~d;>qa?9mg5%g%*=6qo&ViRARH8mgB<>jE)+kHY`*7+EVz zrI28gxVjy*jq{{>E9Xg%2lb-Po8PO4KwNwmZ62FB4ANRU0I9@xvQr#$xF~W#JQjgZ#1D zNBv;g4RYfJXpjT6LEyz#^7SZ*?Yk1i9}95+-X3TwjaNy32866=WsJymMdkIWHRbY( z0rP%YBTX0X=~!h)*1}+Qr))02SqEI+GH|(moy6ZZ^RkB-Z145bClz6TbIE%!jgDdc zyFs|XX&b>Dq-^dQtvmaLjUaiX3gGYTeKtuDaCCBHRj3*v9?9}<+a%2mfXhM2Tck#8 z)LXFNhcHN6z?)1y)hG-DT z*zr*iDWLZrDYzV4K>ORi2Zo@VI=;qi_VM*cIebmr2Ymgm>Sko>FT`nc39ty> z_KBoEjr0X3+&@{i+x^uf<*>j|S@fnIlzMa1)!=UDhkpk4 zY=h_FmQ@fGw*M&fl_rO!*5I@?=rStU`MCs-P$m*U%DI7THoWSvrl=DU2D@nM0E~W3 z3Sl{XOr)=im)HWeh`t&ibo7hIrOGy8J$$N&Z~i8qEVmn=wQV{nbrN>y8+)nSu6Bd% zy2jQIm8qw|+_tCy+E_WHg328D9}e;mb7LQ#mM*iMr=@>{Z**L+@H625&Xvu;3JAs? z^rhL%)R+94N!Rh-JtKvL+5TqN@5AQEtl7@mfl6$?1yzgErxcCKD9XuZ>)(p3!}brX zCso40%zycTTd?o0Nx^pQo$XC5;_qzHk#zW7I#fdl%Vjt2OLdUC@nJMXBMlLPbNK|I zyjajkS065b%P9Pz>cHY%EtY?2GLU!U{cV6+GR+@+v9eKu9hcHo@5A1FQHH~+2P(j?5@g=v0HZktoM$6B-{k2x zS$@7ET&xLfDyv_e{4Pcg_RV#@!Lf2h8%$217&j>Jwm{$dP(>mutS`sH^*$&f_aYnT zktuIm_(z%YE^HwC@3ozL-{)y!@|3L#g}!p|mfTP-f9|_7sJqdux+_!OCs?~ia3Xx0 zJ<&)`hwrojXG**+=HzSEC-RhCiS}`_@AMewko*((ugA%?h4boScvhZ&F?=&l4hhZC zU0ln00DB|7Y)tME9LIXa%Lx#35o&_X-@9@p;f|9Xj)!lzm9XRzSz@&s%ZK3Qs84;c zPf?rIOpt4v*8VTE<_U5m+pC&7akFB5p0Zi-LxNo1i5IN>`y_(sFsJS=g|L~4a#i7l zJY}J}I#FJtvY=@AnItf$l04mdB3hYLbyq$lA6B=0wzInWf+<`~@ZYsl9I8{2! zngSgasKcXjf8j`;vV#BiQJ{ASnwpzuqh|7}5Q$MEb-$V10v3jlF@!B@4v>GT^xkVO zKkb9Wcc*`~fYO^PQT)e8v};Rwry%7k4?ya-k~;`7`N{*37Ht3rO7OwoudU>z{2yFH zVM%1Z!Xo|y)WH7L*y8&DQEepepKav+HX#M*AB6MWfAXbh;qiR_TCp470my^vCjHvW zQ5*m%A8qePWdR-Jb3$&uaxz>sS?&rOTK$qiYmkRLolKTT@qZ9=UPle{{f_b)VIg4h zL3?K>5X09bk)36)ut6<}>jEWfRWTOwe^$f9n``=;F7h7XJr!&~Hz?Vug5f^^rb&Ai zii1kPtabMcIYnOu?b)2>qdliJ)z^AMY`7Ok=FfSNI0EuqKu>Dh+cB{0Jxa` zS|6Y9)_GMVenTa0C}R)+wN-%lZ$Hq^LGmj2pb-FN zL%2mGQf-JLY^!`8Ap)Y%#0iQc&*YVT0>pp&f#h*=I{_Xyr;d{+ zK!{D0v+j5TFn+u|MyOMuSogm&fJ`Wxn+e+Bzx`zXfPdHz8FIYPSOv|_1kgqtRAakd zmOM!4ssbF!0)S2mt%eie_fFPff}CY#-0GYVE%BcTvbz$T@5u$SZ>?<~@Rv`gaA791 zj497=1z={Qm2&@bdsrcwATKMYVw`GMDv~F|85ym2j96W5%Xwwj+p`$zeU{eCmvwoI zwfO{xu&P~~g~hV8N%8~u_zkI@9hwYtJoq+fSpp|a0kWG5OdVP!t5L7R-kc&&6i$N` zd=T7_^_U7B;|q3inp~URp9@BPyg-@zUVl5%!G2m6SSv8=Sw3)UbLt};8Yg-OK9rZj z_Xgo#!yFIRd+>HerBwD8RTN6>yXnU19hXKpRG=&?$Ig(i1qd|?S>hB~i4^XewENr= zRtMnFSA9z~2mR^_LwcK40BxR^yGm;p4&rl6o+srk6@|uyNxJct0yH@^EUfaX_y&(sC-N}DiS*#o4xzFGM6r*=kTmq8_j+}{=hP>XPkg}SFQld z624SroXg4^2fYWFTv-sVLd*C+fE3FbuL1@C1htmE0kTH+eMRVUp{e7b|M_*5JT*Xx zhZ9i5^4G|TN(?if;o&L+YkH(esYw|R4d46$MBf)0E`uty9Rk=N{cNp_UufVk>K7VR z9dukL-?a&zBEVWS);3@%bU$mTa7V))&Sawp-70=EAhIReJn;hSVQhKZIMGX9`U$SA@B z;jtptKRGCr-Pt4`7YbFuK7B_Hsqz?94~LXUzmqUmBi++SwWl%58b^f--`F~Z%lFe}CMEH=@!R5jOZd3SL$zl21WOHCVJG-zA)&ggXw0#Kcz<4TMi;oZRR%IV=lxwi(TGR_yH?H(v zk%I_HpbX6*`Dk_Fpym}hh_6rn^NzgECR8g{?D5tPe{W?Ccgo|0I%>hyor)8iyI+*q z0I%#~oxI>FquE@qTu{!)haIllyYkaj-~bU|+Xz|e?)p~;!Gc>B)2^)F-m3K(Sa7pq zlLeaxKRBfg{Xi}jh7~Ku>-|8U!7VKCGdV&SQcTos*^G}Db4c2Zlaw6%fQ4^Z@&#`@ zeh@TKNQqj0Ktd(T`h8^lfCQII7*LE8OYfH-$*7J9|(_sL>qv;1uHuR+2 z$NxI-`;&5#@Kv!AMW!B0`vR6^XFw!=TKL8n@*je5MXliGm*C;f7+aCPHtT#wo+I2T z)-K!)%B-o*$!-B2I1uvW%y8kZ@+1T>UAX(N^2vp}%9E@v-1Yhjym)Jf+z&6vgcg&O zJ7SM2Rl*ap^RNvt;A^?DFhB+AYYEcl8vw~vLB?5t3=!t2r8AXM;ZgWsf4?PZlJTyc zDx&3Gy9eKLhd4=Dqc`jt-Bj2LcRTLG;`YbyzQxoUMv)<5U|Pz2%!%A3vKi;IhOniO|eXs`zsUSzrQ+vw%n!Q;%dK5%#a=6jnZL^$gcB;nQ7edFuFI>1D=Nef3iHqX zcg%17LvATlnW8j8*q?H5q2?4t|GWPL{X+?g0DsYrDo#0}9V=$4!&j8H*_Djovi+C4Dn+WvcBY4siBAwnrZ6otitoICXrwq+C{#GEyg{OXG@j(^7NNbBo}*+f=EjAT_se zTwXy=dYY7xH(4so8&@C@!agp3F*?< zyxd7ZCo?ZMHCrm2T3D2xQz#W>q!vl}1r_tsipQq2xgQ4vcP(rr_3oWgD2-3gO)mfn z(xlXa%=ENI0G2l-<(K6I;bWuSISNwpE?$}NCyU?Bqx1DQAS=`Ay-auZXwi~nwgtA zCObV|dMqQo5OiArnw^|iFriSIoDNFN%_{1gUB16M3(S zU;gy+xyxrRk5xX!_U06v3WudFhFOSq>k`i-p@;Je4{h%bEFL>Hy|56hbz*TQ^d2ca zXG}rrShQho=DF#UrTo-_)U?d;IntP^Qf5wmb~^9*0KsbZs~+wugzjIIK0cGY)S17vxPY%7|aCg^7Td@Bhz>Rof?)u0`Kd zTXdXti}FdUqdoX+a3tuTR(=xhp3Qv`xK5w%1;ujL!@WutI3KuS3O+0s{Cj3DK;~r^ zN@I$7uHUJnvU#c67~D_gfuEY3!F}A=yz$Up>DZR3X{q@|ygK3_C&zM6l%1Z+-6kM` z4+T;gsRg-Ub&8dxOZj==>Db)S?$FtML;$Yx#&NqI%gsQ?ZBhEzjNH8Jyz!Z1`FK&3 zIzCr12IM+FuZUYFl#D3`;@qysrDkRq7eLpb_A!Ji39PFiFNezuqXet|NqE@*TPg#s z{$Em=&h|c0Z7;*x_HdrjSDj}hta8V)KmV3J?81(ShRQ3P@02M<%mfjpRJdoG@orWL zOjmjqc+LLl8+QJ#yr_0HC|5TtuEA7H@oV3}>;z6%g+eb||F;|}OvGAS2LK)R{*DNl zjruD%&>MRXPWPf(CbrbI{DKNCd6puXLN0VFo4YaE&DL!RPGo~0$c?ST95LEV?4-b+#EC8%$x29#ThdM-g7mu9sB=1NefC8*C5)MZIl>!~1r32LtdHCKvS zD@Bc!pted;Q>Cb+QdCeWDyI|`Q-Vq(4L>?+CzK( zivRjXg8H*QmLQ4XmR^M?XynWB7dP@p{N{d%=b^cG=Xq%E-+SN}ntKknel+*+SonqJ zev(^1ntLF(`FL*g4xXU3&x39;TQPV1P%@f(^NvuA=Dvq_1~hm4v_q9X@b75x?9N!EBs2Jxg7Jm1QS=E=`IIn5LF1^h)S z`hqNcB(#~khE+Vd%#-6hInSBF`)BAF=5g+6Z96RxywLr z@f>#<=q&~--U9xe>vtBf^IzyJhH;O9&I0%Q&{^;uJjGe8@;QsFZ}_j9Jh=|Zf(n^w zO<31Tt`@d-EU>C8rdIo@eEWdsH-#ak1AHFqoE&ZIX(~+A3Li5SCTWEuO@&Rg!VFVk zQ>_rTkPQqysuj*K6*kifpD`6S*9sS#3R`G}t4xJ37Wsrq3xzZqM<#eLZYFMO@%~5a1}>iXA7dC zuS|tRL-5ksfJroT%~Ysqi0yZ}WIX;P?yrTWBte+Y9|uO$QcX*O!(6JVNeEL)XDg01 zD=`9G@5?+n#FGO&`IRT%^P~o!<5uKJ0#9OiGJq#NcruYE89Z6WlX*Njz>{}*@;y(! z;)%dVojd%OhySX_lfhki+Lk9pJek0gl{|TlCp&oZ7EjLb@Z>sA>hXzE5KnsW zqyta*q9|*O$hPi{9>(g{b+u+quLN~xtLwUYJ06`5Wfgdd~=U0HF%XAhT;p*lXL;-Jf3+m*2mlxwc5km8| zSxRV(9}D)LBiMy^gBym?sx=fQzZabE$Tg7d$lA+6RUBD7TcyqHyWEpmj?)$Gc-jCh z3!SiqMRws-a8-8I>1rT6IbC_BJ{zQe0WMFj6J05emnq`K4}(1{QgZbd)~T>B0qlpt z$#6n(q9J@KsQm}QlH(&2%8RlqMfgBPd7q*<+30tJ0(n)j>~P(fgkW_`?I#nBIJYZJ zxUAB+h%7cI$a`128agV?0O5Tth|I3{xP}M;GZeudnc){K7H(+Ac-Y!4uF8%m6IPXI z*I>b=Vu^qSA_@^RSaJi`Y5TXUts~Qf)33fOQy8b> zjMd@Hb<8(`|Iq-1DN(_n)`36HVj8(39B-R&3LCk42ydu38#SB*o|t3-6q5XPbTWL! z7F$n@chz-#Z6c8o@9HX?RY{yyN&GXNAqi*+B%vC>nwXdnHs{5l%8sftjcqYJ!PQ-; zG*fAdfSEeOX*bF3aWpicY}xCs&+aF>Vue^0FG`Qsr$#2SsR>_{;o_ih4w_f+w^ z>G3+83$E+PGodWp5A}V1NvO{Dp9`)fWUI)T3bL?D6&iX77h0Gxot=n_Y0cK14X&j0 zJfHE|u7yjiZL^?YHuCG>7EZ07*H-&E?bb|zk>3$}x^Tu`+jeOy{z4xHyK&-xV#;98v$*|z_HnBd0hKGs3LI5v1$ zr>cF*5j)x5L0R;o z#KBIk=N*k{%`gCUWVzo(R0-E?Qc|_j2mtkWC#)j!wpF04!}b1uSx7Ehw4G(VY|+it z&oP|}*8h7s1!DSL?BVKIrC4E6J3*Yeq1B)nH&xS69b= z6YO3q*z{hm?v67i*i#5A6wku*Xu%o9uJ&{#lc2q-DlKnoG)Zv{cfb~eHrk>1|0wm} zh035E;c45eMh_rxSp4^DIt?;hD*|A^%)HcIJW$J8puLIH{zI2OEI<+;XIt-w-qKqG!IO-iQ;ww@KNCmrnb zQ4?&E0T!CJkE6E5+ z7A`4rJDgEaH_kh5E3TVdn}R{wcWtT)s8_iN)4x|;h>hXZ81+GqH%BY*a z0*z4HcJ_OLs~-U|&zEc4Jslh~DaSZpK5CjT$C>6#(sgy)8?8O{&v2RDoC5Qi zcWHL=RM+D~S2~oprn)xkiD;4?qC{|ZD^1tU<#m+WO?OSxQ{rN+d>*~FxLit7E(ELST7 zHAUNIyepJ8u-b!&LAac*nDyv=&PTg@+f01sA8$<~eLa3&6 zh}`OhQ`6b`+MZ-F#cZ->``_@CE7y@gE8+GJpOzW*w5u+WB#wgM`tIeYUDs`nb~InJ ziLNx8+k~^FNo0!Zom}EdHc(USVxEgit78L9yW7S|^ISGZ8m$hS{pI;Ex1K<=vDsUj zxX_`FUf{Zg-rXvys=fCSG-@ zl^47A>WQJkB9`bBR!YfYN1Cz3MLUv-$xoKJz6||0psf(pU`qbYFx2d!r7$Y(reu-Z z_9kvQ4L|CVWv(3#T@G@)X1R{rZ4?E$y}!JCZhNe7J?;30q9K!iuYl#!_cWU`$yTq_ zIVK(6u9dKI)8!~_pKKEB9Hq;-beds^T1n4m!=Bg4t21XDLKZ#my5p$&6xE!6(_q|4Vw`Jr7Smk=PeT35OwUCW)$ z6ajmhcp5{2u$|2?ggmx$Pj+pct7@b+P*K5fOxHc8Y_r~V5WQJ}6 z=@RwC0yjmuSi&(^oa4v;k(hVGTdpdCo|@A4%uLWGV9)PY|p9p6i^WmsX^XtC724D_{W4#zA2JF5MuY!~1rZ zYnPr9=ayaHt#dlvDNR(`pgpcQnjjWC~v8qE2`@pqIPfTfE zGujGD8k^S)V`BK74_&t%`za=>^~^z-)PF*=v1Ri=(zUD(Z{bI-Z}gNDMpI4l?WJ@t ze(a(XdcvUM?!^>yTk6aMHt9NuDI-m_5KHz^GMhW?+TMwux^CMXw<&k%^+x~hN^m@& z*(VO^<_0>HHiunvoHWP6w|{lm)zb7?j^Jll)aR~dj?ia_lTw{MhA9eshMhPaUWctK z^#rnn!O?YO(=p5U60Bz{!?{b*)co}2SwFCgRh>@!0PW|l$nuU{Tz%C20xIUxBQTOv zQOGFJlyX^~KG6H?h-luw>win+)G^m4Jty3_qEdiu!^lHh6sH6J;J^4{xz!0*OhqB> z86Kyh4cihD5=Bn^l8O~2q*AsZW`Belr>%)DBqOvEP9Xrxz{5xrzCWnRnlr9eu^61A z3|z`TU(tp_u-u6q+`+8=S>0xgZg9hs$)$Fo0bA5MxVm!oy_hnAYtDWw_ndCc`5Xno zfo=Oa*HxQi4b4{uw$7`KLh6vgM|Wq#zH!ZT?4-CjJLqCU-A-Zpo_F!eF?EK*Z2ZnO*rCf&m@=cCqG-sJ8OFqv4d$qh zN1i499GU87V(K2HUh|S`phK6VFl9!&L(z~aGmMF;^zVVGC=*lNO-#uYrtmV%nRPh| zQ)VEL_kBS6pujLeaAr_CqLqhS|bHB8e9o@S(!+M9RxUy%1m- zyil$Q-|vNLU2#jS{x4DC#1)wdP&t$>vwFX|;A<-@C}DKwQ6cU)$4fLD?Rm^qBTqWi z%D=;Awk}5-Znyl;#ICy*=!x+*X1`qjUz(=>4cEZR!V!JbNdBc?&w@aky03nS@<$p+ zAL(M^9ak{fv}mA*>q=PTY09?)ZyV#l62! zFoRuaP%oTd-J~$7r<`G|);-t~s8mAy61K?AdvG{ZLzg`=GNt}gEkGLvqoc@LH(UfU zmsp48u1b31&_XHf+s5^(kHz zr8HcRXm?klE_1`3igvef?4&GU!|i0lV%+tJrN2W!^a{h6c3;G}?+Ay=)Yr+sefs)@ z(BZfCe6v++Lq|M=z7CowX!@EvKsEFP&CsoAJVcu94cwmzH_DXek_&>w;?B`E6E9Xl zux>PRQ^)#?3CZtRcQ$f!$I21P*S#8j2v-SX;@tBCggT{Vd6_?Y_}C3CCC-v4Uq22U zXsW9{h#+Y#AL|WFa);Z(5_u_K9rVO%)V5+bf}$)fTWHMz(NI7iO0!N6_;=IcAu+P~>QBIp83kL5`_}f@&9N zj(b|VFH{J7o|mFsP~39uLSt?PAx-V#Q5twrwyFT~uwzo@sFCm(WJ}V`qakI|M}w+b zajJW`Q>7a~I)92&o>0Z_-s#|`ml1RaD>z_A-Hb|d9HMe^zngT~xWn7i^*%J2LG_>rULc^-z0+m)L;x%b-~zf$b=(>yM=x{JH9<4>BM{0GdWqAiG0 zWHbhTSHU|sOIT-9S2PrYuV_+O@9w&x{AXIx-1-s8>}>!bhx|Wk0JvKA-tF$LDL6vr zL4z%T>ayU81?~qn>*em}s7JFo-|V|yy80-d_dzfBHJhFk=TVBakTsA}=8RfG5pI=* zm)z4zaptD%*4Mqy(Vo^3*iSe6(xG4je$>xB%;p$KaZnK{1Kb@PLuocwgw)7FD2nW@ zG|=7AKo7NHh1idhKk%5l7iqB+txRdLzK^@VhgU*cw%TH&h5(~a(rjcj-hxqz?5*>J z`>25)npXSax~85&DWhqv(*qDj)m3t}5pFvfbaXn$j((LTkI>DnbbTB_Zn1YpxW^DG z<_i}?N4lFiyp%m${shfr7e>12^5@?a1}Dx@quj@Bj*n{U&l^Fsg8D*(QntjvIaT$J z8t?Yn9Jcw!p57@F?4}CM#-9F7rcMPqynC52;nn5fsuABIgi}hm+_;-nCM9q91b3l< zDHOhih1TwCVohf#ycLvDc<=HY_gb5yHDwDs_UJr!Z%0R(eZnU85iKgFxZbFI_bdZB z>@N2v>ZEKz31fE|QJ@1Ld}4P=U~rMCnPkLXl#)5ktHt$nH zotbQ5vAbKjohp2iySrl!tpLZ?rtl6#ck!TSdy6V(Qaoh%_9S%f+$7yHl6NHH_$_?vqD@;$)nX-L9N!H6feDQraQsr zIHYB(UizO|?g5SyG#gp&V!<*+_I^6sUDZGj&91>*omG88DWloV2LLjhm>4}f*IjIL z{6Xn*&+W81I#N8;_D}P{EPBvv&UM3H7F<(gKi3N`vNbOYm)P3p+|~8uu?4K? zw5PT47Lcr&o(N8OvYo z9zo=5OkV`USGkf{hqr^P2%V>U#h2U=?7Q=HcJ$TgUs(KFw@0|JKnpchfj2HYRxzkH z>$5RBkeyoVmW1mFFoc#RwQgT%EwnapnsZ|8aW z{8tW78u0ssr+D5rK54kce;wpYpHTja_LZj~STnk3a<*FWUmN+a;r!Pj{%aQe(jqEx?n{yLQslZ6 zIW9qNOOex3RXX)ioP0)Srb42j zZKgt^q1~oJqM?sWg+xQgOoc>4=S+n}L*JVUiH3eN6%q}>m!0)ZmZWJ&uq`x(1!UshTT}se_=$8o%|QZ$>969Ss3mjh>rpou%aGccxGWB zib4DrMwQ?*rmVb~O3;}29qu>*b}!%F9{d=4a+ll1+Es()z=a*|#`b#)0T8!0Z!vjY zbUQX@XG8@ye5ZSg{SGPmZm0XWz2+hfcALYKqJ)pJ^IY5&cPwHN@45%tBMID+xTr3X zFy&I_R0xZgy?nuA00*XsYVa6RBd;5`rR|F_c#Qo~LKG_Rq{NO%@)w+Jg-CKxL;Tr%v*JBK`odi9G zw2FDur zvlq?)~TjU71W9%pwg z)tb-eaVs`1gg&X;Jxr;m-s0B$t4J`H?1&2U?)u6-se(O$WOKLdOo@Cr>Ynf1;{xpM zOsKv~#MZU;|H~7`Hh=HFWbbXjj7sUKUPH9R1a}T^ivpSYVJ?1{?CtY|`)QjndZ~8( zn5fTp@oxmFC-JH~QoVhgWOa_5;=8t|u`tw#?mrBNYk#fc{nt1wP>HsE+-pbS_1W$# z?t4PXQoI#m%VY9yQBJ}>-1fsE@o8iI$}xCLOZI(N1U2@b)X;rAXd0{oYq^V8-F-qf zawr^CH45Y?T>Yj~2$J=IA$PAVRlXX9A56@Ta8&mgKbW}QiZp&;eE;6?>Pc_FDY?3t zqN!420@%WO)@WidY((WAMv~Qedx{yIXn`&19TlnF$avy6T_c)NEgDf%U@Q}^x%&#| zb&V+c)kJPMeq|KE>K@KSxZoJ7wcQybj^Fg)ext+{yCAA)SHeG8fMu{;|+-B z*WDipLWO12^a$5a@|%dLcH1(|(~!Q?)XMmJBAPmr^0nLjGDT?qAKg_FD`X2PwEh#z z+As6GCp0We2<_@(thEr<7fH06i<&m0Gy=XpglgP>%e?`DfbmkiNJ4Q*?@_-{Mii{^ zmaLJccHPv`)GUO=O{EV&L8ko2R->m{69QH}JcQ zXe${;Q4|ZewiQG(*h;#QfZyD=26*VTBP(PJDX6VHx7yQJSX!14+HJ{2Mjpz$bfjH$ z)Y@Z#M!;t)e5iu0SWknnH+dnN3Pml~R5aE$X_OysDwMvjp$Th7Q-N!o%Kh8=eka`1 ziUiRz!}-IJ%AN$l{yAX{<_~?u4^Dwq7@Ajy+dC@EHkB=?=IKiOonfMrz<9J1`(;Ah zKif%MVVv#s)UHu#t#Ogy;>_b$yJwgE50VS)4k0X1g!QRWJ=pl_fKX{U=un-m%?*T$ zM}2B|TG*?T+$A-1WGKS@8lG2m6kx*Fhebq1RwMNW5L!3pM0I2{_2rL{aydD=F?+L? z=deAV=E$CG5APpbFZsm;rNuj8plkV^;{cA-b> zdSV6V3tBe#4Qv7We0_R7Pm91q@ElP&mCMTG8zL{WgY`Vk?5}F5?Bd?21`s_GA2_aG zt~_x3W=R?!j?Mb9+*36je#LAqdJgamaV>-S1ToiLiCvCY;u@$_IXO1h?}+(5VP?iFND z8=L(asTkRr-~x7Tl3X;*c5WRpg5@0n=WcpB*o!V%2=EIbi@nGS=n4Vq-__IDJ3h)& z-)0Y60RmD7v^Uz5Z;vFooKf+6i)tzAt1+J2I$FrA6;?1Ijm%mBQD(VQ^1f2vQ`u&3 zM{rTAXB&8)w09x7$n0ecW-02)hMprjTF9&wR%=2UnY98kF}pF&6K=DQBe=-ywRlgF zJ%{9?3G8mHGXaYARb$UjIx^^+!V`4}V+ld@P1E(|lsn>^L@OI9p*F&o)Af=(-R(B6w%K=(I+2r=k9vmN_mEsv zX|HBF4NT3dqQzH@b}{%x15+($Lv6+j?^C4w8%dOK7K42gT~! z&hw*=4C-%TdmVy62%`Re*Oyc7h)FVonoZWYr~_DI0wIoSu8<7Y*qr2|HU4IyI)bWN zBhArUV-Gg6qfRKw4bI;_?&$g5{urqjxw+H{2BTpl7d1M+vyK+UdZV-FsE!P_{O=a* z_a{`b<*k7FXh2?Y^FwX+8CniQ7SDDAHU5j_au&tw7Bv!7@AKU~c0Dm{`g=Wel1(LK zvFS(j)RhzV_)5VyQxdI2p&I7{z4xDxLjt&1t1(f0QVVQrdqjxFw^n`Z4HU^xHyvXAGg{Rqj$h010AQpzyhrKqsqn!qyp z!SwE1f~wW~7yG%NuHLT+7|t|O`+El2?0=AKY~ITQJZ+-6$^FdMJ?-ozBv-?3xtNVe)nPwP;IOxZjPazi%40mU?JG&qk};kkWS5a( zk-ZMSsf^oWUB`L`R}kJ{W$ZF)uc9d=m`bQi<%BT@u{| zvm#+33*A4$y~Yz|iGoj{a1-pPk(2WFkF=Llnka`g0z{{=EIr$E+dCxN6KD&&%0X~x zMhTR=i=;95lScpHyGWEi)QJ)j293K&c@Z^4_Swh)WmlSPJ6h3sh{E&pJpF~h=gY92 zBz}1l*{Sio=C6qDSa0qkn!(%KH3CH8+=$g(P<}uXmcXG<=adG~xq3trhApW9B9C#; zD~BX=wnRD_?u8w3df5)_A%yNLMsxa zX*r27q5WcZxzN+AJa<)8({;2c zR@QV_$kPlQ(7RU;FilHV5~?_$TLCR2K)C3+G{dvnet_hjXa`@TeQTyC+5RcX#o0#> zi&`ma`Yc$-(+nIsJIvMzw~tUoHm#^qHp%$O9CLKEXj^eZg5&y*b3B=4*bz(*6WNE; zJdN$Q2oIVa&189Vb$0Y80Yf|5G1t>Qz**r1ze};&imUgur;SkK1@^?#o)~*A4c52! zhF@-RyuiDBFCiTMLg2`rS9m0`s#%43xp6spY3a+$*>6kXt$=YM9)1Xo`x*41g>IzQyAr_bjt;@4`Mg^NTCtUxNI6RbZUcv zIUeGZyzGHMn)Fv z^DIQubcM~AVN?OkdNa(m?i2Af*rq3L-!xt-h7UG$vD67hnYs@g8T+GOp}=IY(*estPe9p3V2AX2!VVpy zAi%=K7d;sGN6-F4G>3@PHTj3kH7G04+Gya{HF0RuSsz|o5g__7wBu9jJgvxCq!lu0 zRK^GLjsL9k*zB>ZfID@k99Q^Hz7EZ2Xa|algZaJ4p{77(yDyaVsFoD;>wLZ`6rQ^^F5<)Fw}~&HLEvp3XM=5>gSi z*wW+Ww-_!^qu+!R*tG-|r(g5m^z^j9Msjib75|o}nldV(*%B;ugOTQFV;-CFmgjNe zb*L0LbG-MK=a$XBmsE!n&R$!}6dqZhv&A#Xewbj{w(54AX+3D2-mRWu`*#EZWqo2B zY!CcMa&Zo~@wQoc6t(tt&l5UYXrc|?(Xspup^7GIC_hKa(L|@b0~}Uv-s((;0N_kVw4zdhRD~vM1!UsA*-kj~YfMm)_wze} z_huv)wfnjS?-X@~*ORKFWqViGw2cTsRP5Gwb&99VL4WGa>b<8cr>21&so#4ZA;3PA zkVWS(dk^d`jv=|+In>|otYC751eIt$eoa8Ws(AvyfVP`8I_c?QFEY@U9!8s0ZxUJ0 z%;+!sK+Vq>h&6l|F}w;k=!QKjWNHHFPQLiW6L0^BkVN~9{}gTpd`@!F z6Yl*~=Lrdx>IrF%-V^o`PiC9VhjOEgq@Q`t+J7eX!Y=J-`*o6mj0`=jvulbl^)Q$O z%|MHO=`8qrVYTLAaJV~V!4gGX`MGDljuzU*v?IF8eQJ+o|f zH(>_1qE8=#t>^|M7bTr=Tvr*zns*$YH_!}}^vmO(-u5X`L1%LJ(VS_?NnJ z+HyEfz44{zMf);>g}Wik&v=5_GiRV1ts+IxdVN`qv$}H*irVO`r?Z|GpEIJMZxJ%s zdhzFUd{Htf=ir==W}u+g^azUyK@_y_S2}`JP&yCemQI#&q_-N@AGn&6zxI?0!k4Sd z@PL<=`8?nkgq??aKtwZmz~e>&eh;{CQ>4VIzGvP;wjyI84_Og=mwe|5wF&=}CC?wb zeDd5ivSYO*wr$ldiEnE-M3=GNLl-^mY++$9fv3VHG1j7rPu6heC9%d%Fh^F`FsNRu zpo5$pGC3ve(4`bV0!hqhp&37!RpoX zVE=}oVME0QL?_rUlU#Jd>;9v&K7s|$a6gZ9n(5eYf)(GgqC;dMblA3=aMOuqaAz)t zTQq`B6u!0nFSh!YrwgG=Pjo?xVS==n)wu2HOF-z6G46iH2Shivi)%FZq3wRZ$>hIu zyWbHSm=}8TC7V4?%TfCNg1b6PBpA5k;yrNJQ_*H`P0&F7+4fE(1G`9cg1L)OtR43} z>vUvr4BY%rnYF`XVkcWX(;eu&_m5|aU>{?samA4+dhL0nR=nfas8GR9G879R8lXcM zrXet}@D?l~RjkH#0}$CqAnI7S;(!#&t_MVo66UPouhB+ClY_v)AU&=eD2Dzyo3cS& zF)FH}uyRcq<8Q}VK03$SSL29Zd4i(f>JnEH>w_6EJyJ<3p(6_KQ%=Hd&a)Ur4F-g z`#;2ed3+ni**}tX*-AoALM}U(Rt}Jmi-aUxcAVIW9VfA!lLC=##g=@?k)J9LZP(fY~L12%h5s)%JKU?v%Avl?(D8f-rwi_N7|j; zdG?uSo_Xe(=XvHCxo2dE7r4AMWg#?7{GYBzgrzs|x?Yse9~I)m`d4$Wv8m~qQK7N! z;#j^IJv=s_i-Hz#m_839BunF!#U8d^;RST{8^C3pr0 z!hqX00Rh%6*`r${c=|5#NhK>Z9~`nK!EMfxYzHV9aRq72ZF6TWj6bz4d|Ba zaHz^=zr_5|d}4t6=Z6}D-`9iSXThBUU|YG@uc!!}5abIOdyZb9qw^(P1=dgJ>Ysm? zd(P&*=NE+L5O%(Wp;^KExTglrxmkeSJ>2W}FAS9h`2vPrZKV#oySNGryFL2nChWed z3@sz(Jl8J{RS}+h7l#%H zzvMs=o}4(pRePWh_3(B$CUd|jPxK5M74(|ByDt#0mmU%s|Fvx8ab$pWkoNY#l6H_iubP$J?{#BpDSiY-MiOf2I=KW8J;JfuEUe7 zweLHphaS|!VI#lo3|)=OIf!iJzo384qsJy8%AQ{$Y6!<;``|#pp6Z7=*ffij>=6)& ztENcwdFw(S1)num{Xv=iQV0@#L-6;8T5?;XuCZ@$&y~jNpTEXEXF_;nQ%DN_gDa(G z$X_(+pnk$VXHX5#O;D?vL&pV+Zq|=m`Nd`(R6qBeL7fuSJvTu;CkjR$$JJsazeYf} zV(ujZT_SpkhtCv;U#{1E-`H>aJT0N0!vf5~W=5bdT0<}cbEPl>@o6^r3S_;}L107c zT0s-|uWyKlJ}5pt{{@jO+uRmf*U--hh7uYSZD)zibPQ zvP+0?9ihfV759C4RtFO0@dd0I>|LA1Jkv==bcTKyyoy7RFu0eD4r$%Y5MiDmz9Dzr=&%btHlkF54#C6@iVbg0f9^xTq{1Z>ER z+>DXjk1J)KlRE|E#w+BeJ{AsP_1OI;EVIQml)58UOJ6?iShjK^P$zB!IiQW z-7A2&rMK2xG;1}@OxY>hU-rR zxL(G+#AqRUiHDz?v*i~r(jm$9h{6Nzi$j~SS)2O+Yg;^8%=^#yYD{9yyEJr8@DZ*S z(^md?Dd=>7D^;|r%XBF4wI01JRIdZWnD>@e^Q`|<4k{yo=%oj^mlSrmJd_Upfh%Qb zK6H7gF8CL&lzGZ;6?~Pe$}I+5WuE!+OWzCmbfB>q;AgmZIQWbmwqFyZ=E7WR(d zt$C@yaBcrS%yWae(tE$J`wU;9_=-@q4g#a*ZGv_MIDqe7p<{j%UK_52aGb$aV0iuK zN?7#fa;1!hw+p_-Rpn^7y~1;%Y9HfXQ0#glC{wvlvHlmm#N&=3kV{)2;uW5yr~M%G zS>e_FwS!JVSB1U^p2>ZXhQ!!ig0^u$6c6z3-cXOb{Z{4y=JNgBccnIWa5WUg_u;EU zZw1fcKBhR)uEF~MBCeE81_vHA4-CF)w;cMu4i+(hB&x-sp>#@aw<}9lxBrKsgYKQT zTKJ)V^`_RE8#xRu{m`z>IzRM}jdgNP+{9-1q2KyZh{Y+P66b;z;Hx@snd3ZuU8uwD z{<#&x?|J;{)cuU{<09wnlRI<cHb&>|y5$}vi65M|hFTo`6uJM+j!>m5Sa4fj+$`T2stE?U0>*NGKNh6R z>rG4(<7*AO8S6H_fLKoc&Mi7w$A6vKGq&FXvte)o_c6xxvu?-2>sYRoP?+SdH>1E+ z<%G(fRi1J3X*(g9x#twLK3<-F2ehk`4WLULK+C_m13Enqi?uF$eX*@sR5zCP9o!ZA zv&((@Z5D%R@D`0XS992LgGn47!KxYhWrY!dGO{QH@b1%9*5Eefi$HKa#qqkj8NPJi zw%wt6m-|Aiwv4|?YfHw6ie0D&t7d4+IYt0EDN(#v7wRFZENBHE>hav(&>WY0msKmK zKdZIkHX{;BD=cygP&Gp9OS>o5{gdQ$jFak>CGmsDhJj zd8i+^*kF$pvE;n3e)!NS{h@@;}#{b*=Xa1d8Y5=MUU zQJuKrYyI`n(5hmt0NuzsnGfQKJQkW^GMR>Mmv4J4G&LCJKE@|!oPc9_em(MNSuQM| zD~@D|Fz6n&|bLCqg4U#Wi_k zMGZajsn9f2*v3kE`BS0egRApZHTw#SR%uY%`OPs-rs4S0p)tb7uFN%-!*Ac-r$ftK zL9Rq`uCD!=t}pq9k_~*{l|Kt19n-lSwrs(3%Fpeqb^jb;E%FVovKS*4pmY@nf(0nu z_I#*}W99F0&sl(yTA58DT`%Ys${d!89(n5vp&MOy%iG@$og`09j2+MElF4SR>$zG= zMAmO!4E1<|k8&SobKiNt3Y{5ziYsL^`-R^F90ObMRU2Lj{X+)}3c>_A{VE2~Yu^^u zQNIp7q=Q97kVF`8ZQ>+mE~U_wuZ3KNuFr@tC#xy*Inw;#K8-Y=au_ zq*V%!Iz-R?`R@P99@ z;eV0w^LF^NY6ko-FapToU-+R8e^F%t{=5qHz=xs9F84iFt@!(owN~6^L_%qWK2rJ9 zYsd17y*u)CI2lkX`#uW2bJWl1A=8@JN7OdkYE5};p2|b!wI+SEEMddRaSj`UqEz-t zh;mIB-sdQ%Nacq=3H{L>e4qO?Q;^(GfkuWd)77OI)z9V0pM}afY7rQqgo!MQHS~FCdeFZsFMD!&)U+`;$wtXU)B00|sDnQ=W98xMGKju^hAM(bbEP?m z?vu95Kl*2gPfRzAdylDRZ~rs2*;_2-i$$tN`peK#_tahTGhf2~H9h~XrdyEj#x+I0 z*CS1n_y4PSl>4MzIseVMH+ja-QH~)I=}yC`iA)F9l~}#*`Nht-K!(M;_ENs@PQ`Zyz~oglmF4ZvCiI`2@FgT=055wu`PgVX)Wr zBcgJ7Kvq7F*WVmBNoE^O?iam&uid&MWs2?p=XkAbpz$bvQ3FI5KzbEV8) z{gz)U3g#2?1?54*q@&%zJLTmwq%wElPWj1&qsjtaR6}>E)O#`@y%3zvK|)_M>bZ|M zzCW!u*AQuT@N*6jqsHk&rK;eUTq)y-FNf+l;&X)% zpR0uUyNc+?sFvr5w}(kyWig>UoddYa5w&$0D41h;%lg!XSd&u zllBA)?l!PnkSj2-8~c=E&b?b+H$hsVuT2d-;%fd< znXqh8uynt6my@(+Y~wu+Y_pg9AY+@zabTN$Tq$FlaRRp4dpBbn*Is$q45{3`Tcy#R zsGH}S*C#`ozRrQmN$XdI?~giO+8g{x^!|s!_vNWld(gW(&y_j&?%j;H+;`sXL=83x z9yc8%4RL^2!j0^7>Ez&XTq&c*cmXv+yOlwNe>RB5E1wUPpmLrZ-kH+2U=0T^hwdWb z`;il*iNPk(`|GUV-y(W{lS+<~-HaUl_^DheN#`c_*e*KncB*{$qOk+}eU?)XSMO4y zQofiig^MELBaVo~GajUi{OWnnczMZ*lEkedIF*$dV%_C9v~u0(Ve$hfN^`jPOq&0U zIpDvaa4pDb{;o6SN9RcVj<~(tYZNrF?}WLM%N6_?R}3wzGx!UxfI6@wG`PsLGU986 zPl5);7ceuYsMb>)=nGDk_#lrbxkoHkV9+Vj1Hq5EQbdb32mi?x5OVSrr%HTe1YcqI zsnT^i2n?^Vpf!KxpfYc^=p_!reZVl_3J$*~Kazl5NM2J8XDb)f&oyW_XHT;_#GNEbHqP67uk#%GG7E>)3_T%-}+9DQbRDs;gA~})6O@ov!~B7 z^Y{j?E?X%-wpi-*%8#BU<&tsSxlD(psm9yOq!Ycx+wy>}0LRdJmG@Viuu?K_I{lH{ zy;3?h_~U$4ZK=)7_&>ZyaaWYAk|xRf3yTMdeHQBW)AmGX3vE4ZZ|~@~+k-iqsKAsE z4&{B%t&&!Ff?SCb7Q$XOti6o{kdY6~v+v&TNUiSTC-Y4aQQ?VhX`abz^ZY$>zZ4ck zFXrp&$nbNO4DU>K@@5>Lmcl}B#++Q6IRxc@u9NO`!uausG~MKW`ABv(BH6_!76||K z9{F9VWQ6?aKdjtL6!AKsQ98;l;#G`uQ(D(np|`d}TH*?}an%@l zuXakQV3I3k#5`3%Os?v_{Rs(2IB_Kkj#D@2aA@VgGCGRD@`&=H_Del1ehf1g-L$0C zX9%V2*ld=_JaJ*WM-m={2oVIEN&0uDZYWkQ}QX_)iEL0ONtA$`@7P3 zco$cfHT<#f=^B0q_nZm+;;inu5v<&vmHrq! zz|~?}bsdV+h-pcrhUvDdn4{=*`O6!<&({k-m@qv!{N9{=k@GtKJtiH$e4Uv|hjMj^p7PXf zV?6s#`H}RTI~d}gF``yD0id?suV6m)M-xg*L|-)d1IOPWof15m`&OP$H$%W9M;rB+sVRK^F7MhYjpBlgyYsIpSbi*T@Q;_| zu9<^F^07BdMRNOp#|6iJv>DycB#yp6NnAJ(% z3G!p5Lk7t2+*I6OUV4kfpRD#zn!?mvkQl<#VjwSi8P`kJmrP$H_a z+wjvwr>dMvSD(;TgsukD)9=#N>2zkmYWi70iC^yBmcj4m6u$QgJwDwz4*CW%zGpxL?Nb-U^)2{;dq*%NVj-8KPSml3Ua9v!M+Teyo2O zceDPPMkHtb!%kIa{lm_!X8ps?R(yau?k4(SJ;eeCSWmI@=vYs&41*cgRqV(n)>Z7x z9oAJWMIq}db`s3J)E6uZ80#q(%y}{O;RgD7kbZX3&tlpcJBxl;KeC;7tRGo)!)ywy znm|9T^wV&AhVH3bn6Z&{E;CQE&LyX~(z(na!#bBq_q(are@H)X($CN7=ZHP{`72%B zM^`t{4`TwRr#28foJK#49he{{c9;-nVuko2&Ia^WutNMI{A4|`=4mr~EVq0!(&VjISS1*J>)2Kis>Oop(@iujzV>&ha82zV|vI@ zXua{_430uwriUDbwwNAr6uQXtkfRW`I_i6621g;B1ZQ~2QD~>>AxELRO%FK=J!pE! zQE0#EAxEL-j1Olj6#De;31QPCjy`Xh9&+?~-}I29&)-cCIr@BQddShoC%Yci@%v1U zKFDosc*xObr0JnTpLh45mBxA;b*2~}p1|?XiKd4feacM_Ir`L?9&+?qX?n=fXPxOG zN1wRqAxEE-=^;m-^Gpvp{<+NbkfYEKj1OmV6#B90AxELx*u#t>PUA&1qt(z)H~qxv z=W6=N($7Bnxrct)X~qm^pm2WyXa>p{k%v& zPti}!$MpLr`k`pJ_)z*eiGF6#&zbbIf_}(`AKyejr0K_RrJtAR=V$cucl!B2-t(BW z6-g-PJPx(1P;Pr%`ooC+>J0wNpC~i=%lKb%t1JF1x#bDz(tbti>@kZ7+W6HGYQ)a-Zu7mf46#o?-S5Hr;<3SCgyy$>b z;rgR|#Q|xw>k9?o7Ye}cO91eQ`>g@q=~n<20boB7K=+{g<+~3^HT3_*0cqa61nG^# zZ9vu!R6q_(r_)(qDwb-GcK4EQQz&;GlumL@l*^t*G~ZhXrO|TYAi}f8JSB~A%}`3m zt{UuMuabdndRrj>}<^In|6HX~a{ z$6Y)6L|0ng{%2{HJa@w2u-XjF7DN)jER`R7RvJfGzw<2Ge>H>QPTemLdO<3a*X_re z;L7{uC(jyOtbuuP;^5ILm`6D<4bLH%4PZK-1DJ<$U~YWT0!)oGc#I0>9S+PNo|i@t zn6IA)m^T@iV7^7arGj!3M&ZGu14@%U56ESc!mH)viwZW`7Xij4U+`;~qz)+0vXY`gsf0*Y@+-8pg8|@}ApU@k2|oIj zB)PY%H9KFCMpMn~E7BO(6|5$8{UfhweRkOcx~?C1{NQ4hLJz1QJinGk5{R+C28jD| zAkO%W1&EQaNn_k^sFkEV~RjRa+1V^Fy6dW8zg-3DZKye=K<{z`=u`i;WG zRlflmUl;-WD-U2|xXcZbl>H7Nmj=du_6@+842_2vX#Q`dqo`e{{}x0&Ms~fYV<61! zD98^FKy_`9Py3xzE^mEKnj=rG4g1{j{xXeXt)w&( zaDBDzL9VZ+$%XN;t;m@!a zsDppk+fvAV?}PHoUrGxV2&L~x$GGk>LO>9a)-nTxN!NqzSI`jS$YYfKVuRTsUNeT>PQrbKhowHQ9Bu5zGz|m=|XZDU^3TFi9G4aqk6~ zDHYNAa~>K9dYbDQBea7eXmdZ3CcFR2SDyahr1A35pA8x4`oIX`Pa+5}eJma2I#M3= zPpML2&C@=CV$n~&;NQBQETn?+!gC&^Wpex{qiFG5E>HecDs=UiXMZZ)>ptf}`AHh! z7)La~(JzddX*9|MriABcgMm%;rz;=)pCO29}2VNsb%293>I-Q&;q>T#fzuO4Add=xoO)o$2(@{C;y}GPEj)}s z&HD$Z?doCS5o5LK z2*9e{<_WsS0D4glG#KydSHg3YNx{&sdtD$_M#Z_r9S-KS0FOuuILGjj9`+Hy)QDLQ z-EHZ_LpO{x%?>=vCll=ksLAo z3NfEFAoDmw<`F$Hi+tgU?)OzVm-)gYIXe19bo?I!)b~VCZ}5jFKn{!>6t0vpP6x}Q z0^t!l3`t>d7d|X+C>=bTYpd^JdECJvWp2U}{UW~+u;`cv3&WFKCvjhxQxs;()bqjc zDEAx_;8`kQt}jTn-gS9Ne|cRn>~pQ-VC@fv3#mJ@Ljdax6Rfp>rKsoQW}-j)zcOT? zI?gWOfCT%8`*Te$WS!zZ&jjsk6|>C`Yh2EtZhkcf_0~MpDMb_7Bb_bX9kEnvUbFR7 z7mB)Sr|DZaiobQ`kq}Kk&woY!=12qXth=5u!8>Szx1Bh=_VpoyREqqKgSvlF*dw1e zC|sl?%ktkyL*0Kdf&Q}s+O=8UFgT3kR%%gq$8U!CTx+SIoEO0K$)$_J!`)*ZQHIml zW5fNpfm&pi1|#KZBXp8xI2D+ncFi0=NM2V1ov=&=ecliq=%5+&DMrxq7-*=O8;0r{ zvVscAU3E+ZGtE^xU&z6iY zmVbE^+H-9l9tz@K_q*-;4^6aeZUN1vW>HXfKTpALE|D*KQaSF3It*yShNW z@}F3AjD6H7&Bi>cNVAcT>Zo>7c>GiqsY)KKt0a6ZAvL80qO8IMtxOE<05XrQEo4)Y5`3uxpZ%)T#Rq{B=qt$Zl45g#aoDm)+Up6bu+Z9GU z&KSt`i)&_v$6^r#&0vXpzFP6wnc@DqUMWy`@U+K`Ja{rdsFb2lU-sk#P5EqA;T%1S z>)ir*?B^KN5fhv<6;#}(Kb})&NkD&f*2K~Bsk0${E>pqXI6KVji4V=j*t^&S=fXTb zRR5!O6OUGf!Y&nndk)wOgZJn;kO#M!0Nku1vg2`GuMM3Wp67m11p(pbk$2AxPbN6O zp9?t8nc)1)1c&KezuPiVGbVnjLR)lFxIY0}eG&kDWCHY|0?4&PE<0H_!Cy!P0oTO!qWKsC+ZO7Ez*SG=_?P(Q=!)<-*TY=ht12*-&^dQkU?$&Z#OQvdb@x7@ zbpa#WZ41JqU2kzfMlTExCLmK60?6--Kz<_x^7SHVf~H#Rm)|YKGHy>LSRP=0fq!Tf zhA#Xv4~FJ3G>jQDIq9Pba`*K8ifqt?_)Ci*z>eQ<9NWk3SLPQE1kvc(#o=Q2N)^Ou z)#0IB$1&MmZ-TVU42h7*O$Y8R8b+83sEIGt0HaMNI4KSeH4<`~HFD2m^2?LMC(E;H z!^6jrho!ndbFbi!d@I$%m}8~-$ap_FUK>6ka|fmY7}{Nz^u}LMF5S5NM7b=$<>6a*hxukx zYRWX+v)403-xb=O2RA+1jTbk&lpDhQIrWl#{3Gp#K0bIq1LmzJSmnwMHE_LhNgaK; za!GxbJ+d>AiZ&(^ZQaL5H_B6&hX-UX|0y7N7!mGKE{O=gQZ9)I|5PrC2qPb2?-EM$ z)JulaS=tSubft1bSo}n}BrIN4FWLM5)^6OFW_shJA7)VftPM5F4X}-ODVK$~+^$}- z+7Dc$m-)VK>I=6?s znsWB8AxF#iG=#?%t72+cRES{CiR)@z8y9Q-gxEmgAS{)9-Bz*m9 zSj!6KCs&6@4xBOpm6*HvSX^b-VN-O!xpHVt_?Tc5w(u&C&XU)z2~X+w%UN2%3$x_! zoIGmkk>G_{v$et*v*mjSjXs$Qr_I$0r_7c2SB|b6gu+)BYK1T3O8)Ap{!^%U>N2f( zGOpwcb`6+GAU3Yjin~|IFC(u$75Z0eg`U;&C(jj!2cU4+nOfmsx%2e!n0|A6w1OE; z^2_g*oIsy>DWVm=h%0$V!N5|2cyvrF9u||Y3yqyj5ResQ z17{%M@Zo76z%oA5Q2+yvgJNjX7 z?jL|V7P4>&5XWOZ1EGLp8!!+Gc(!2$V3~}{Su?;rc!lQ|R-oqWFUffeZ40B`UNz~10HpA~dncowLr^gMU~ zb@-lV1$?iw0=~yt0pHuKK-bfYBH?N9wwxUa&-X1M7W>z}ry}7$c->PE$h%s?W&LL# z$ZhYLdqDnIOZc~w7NIEXWpOdR@oKv9^h6`c-uM!__C>pru};jgOApAdE#VdBk^{26Yo_1x|Bx+4Urx^>t=WG^O-Aq>tfxlmh}tE6CE9q?no!S z!JuS%#bD+qu(q*6!&etszdqWo!4QM+l}D1vXvzwPXKkXZwKtNnYfNE%v@z11ibX6j z36v+2EzwB2*&Y{9h0{q8Wzl34Pd;7Sy)_xI zN{c-R&*JF%^;TGTDx!?nY?|R;6>D#gMLL8aP69Q(3!}|xz8%r-_zK_|UxlAZb(k#h zpVdS`H$+B3TePP){z5JtuXZgjoD6(-#c#%Pe`~?G2~| z9a7Infu-u9*j%qf38WxYeM_Ut z6xM1*-cMynX!3sgHCv!C%%n1dw4X&~nzVN&RH>O#*@Cs4gw7V!rAZp=$p%5+(VMZA z^uhV9(ax61)oF$0g`>*7%1N56iA}Dt67-qgtf!$nlA9~Ua=s9fBHB86jkRDbP`+R{ zsH)OvN{?aQf^3d!6JJd<%5ji@sDU-<&dId^BOI6*mmZ=Q2g5il%NYZxGc<-}{2L#! z;SmSqitg~(LmZdac8BjYjLVDZI~oUGN;m4b+)CGmarr&={P4zQt!P|g8lfG@96gMq z@@o3DX;dO&W?(uz;tsOLdwzJ-I7H@n zlRj-CN5KJ@@xsR*A~`>BwDRCSodlN5sj%JVJXw<^D+(6QmD!o%s-5e2NuU7lU2bf zo?$9A^sT<{Ta(_5Im)UD1vPz`V366U$7Y&iB(k3^z4fhW_91aAmhig2ac1y8C1Q3D z8I3L%vUV#X;Ue~Z zO(a|*Kbe6BcNrBLWWwcC)_0j8&^3ydL^j7dVps-PvbC=^*3=fw@M~lv!LDHl^9l#) z8>DoAtp>!?%~;qbqn#1T8q#}+8t^OUhkFf-br*eBBj9ejQ5kCwT^ktdUiSR37|WYk zOii(3D{mRK5l=Ps&`7372n7>g`4uu1w#QmpQ_+o)c54ca!K>ObO0aag@WSv94J3Mr zKB{kY?K^Us-3f@{#~dZ?+H(jI56(QaRO5tXO&H_atL^!enyf zfV?3)(Ar2_8!y-dP4d^k-qf5l>37+JjjZ$4)vtF|G?{b&<;#4#k!w_PMiT#<#$2Hy zX8X0KV>AtI*c9!=j%uSd#t)8&Nlooh)lS9k*{wj{{^_!Cn_(b+mmi21(~Un4i3dAp zZ~W5#g>mUGhjEeDL5+P?P{nL8Hd4(4Mc8sUde%6b9oI&CNK;lg&h-8HPT%+9`Br;^gMqp}(SZP^ihK>}v_O_*&brl6<2FOh16R>8?F+;FgY`acrH|6=wz&cj*cLhfXZkRiisox2xsw7u+T<8RjHP8o4yESD)ACjach=> z`^|oYXMI(XMACY)C|JdC6l0NLs)L76wGvQ$u%<&uQZi^O2%ZK@DV52s0|@tS#(78po5a8DV1?6l$Q}{6>G$EoVI=9%3Om`K57qc|u zX#e6g+`HB+sWG*pmgr19u^{>(O}!~vg)uE)sR48^3}J-;(EJ4UL26i*O`F!#&n%P5u)I&k9CSCxD2hF3ot*~6EQ#w2|Kk1 zE_R1e>{mb-R5wolbR0*y)r^>xoV69-s%U4UUXrl!r)iJwN{3MxAm386%?ycn7AI|m z!GLc>nP8Of>owrMsF156QnuK3NS))r0F0iD<;d)dVDPSvb?NDu=WMW*o#Mr0N8#!W z2+?FW(-kM)uj-*hMJzEfGzVfl#shv9o1OEGnG2?rCk`Y~$BgO&~)dZ-~} zzrG=StAQR%d3r48=uxlGW5xe1Jw_8f&Jxn2{{eZ~jzjjKT)!jyKL%2ycv5WSNU>QV z#g_kDQbdRp7YRu*Kp9AZmaf$FX38vhXd_6zerNbW15vK!iE6viLB zghV;=fIR7z@R&pNu$_HN_+|qs9_LB1pCiQqg%nR6HYvoqSHH8D!k$%!{Djfux!i1J z@GXys|3XNIfd}MIZ$0E#+-xfL-zfgn?3?`qfQ@1bZv+?=*ONP&Rk;Q+$cO7f$@>C zWs7XsA$}Bn-872~RzyW%S2EGjm0F)jILL~lm56PDh5hwi;hhHR97CVXO|GoOv0lE6F@W?}y8b7)#{D6Tbwe%T{ zCd*ix6`Iu1wSguL?D^r*gm(3qXi`|&5>2*5I(1%l<3Ku-zHXw(&;xSG?n9nu+jobr zG*Bc-pV26iVl7rEvXQP06xqz4A09<$dgLe~Uv^J;yrnd`kUnT4!Z0>$LHkbI6Q1NY5a$~DyhfZKvc@aK`4PL0bvGhZ=f`wi zsO@-2_Qr3Z0)M2LA_0KF4!UKbJn^0EvN;jM7ByCjb~vj$#BQU4Odaw)v!DuXQp{OqGkKqb ziL8dEclx_h5wY+?)!Jc^B}Y(L#mpQgc;55Hi; zDt~JpP;3P#@4r8MpJ7lP`5f3(8&renCLfY9gl-Sl^IMU(yk$MB(~%5W74&@LsZneI zHnc9N;+*kWUu{dehuN77fNEP3P4>JK$TY+@#xO=LBi9P*W3=hZ1{qIPENW>oD5$Wv z+`#e!%PiuKHsB+|0qI$sNIC8Ptd82)h6}4Bn<6a;`O0w~=gj3jZ{Av1!SVw!>sn~; z8#O50h8!46ownP8s(DM&@und#n%K-VtqfO&z|r!j&yPPEhbbJA;X`iwY4||{$9MA_ zpU$&*d=p(8=GY$g{P5;j+7HOhvFt7zJi7*NGPv|(opzeocj@~k+8oVjBX8T_op`AB zj^z)BA2vi>%k(Wx6kN+1uFS93F(kBz>+9vRM-Xv+BNZAVu5Y5U!;6zGC`(%UJOWjT z_SBXR#!YrRPzx5bSHy#>Jl(^G-{dBTyj)it0>awv3eDR92ZGS$fvCyNo1!f2RS3bi zFpNNyV$*}T4UJn3XyK(b@tUqI?|k)WtgI{ zjV{rS-MhB)f^SKrQ+Y|)_5Qj{0;ywC4xR5QOR{iMA&i1$P65SgD6+72G4?DYZq}+5 z^4R?t*ut8g#Sm0h^%RNbt&41oY1_@s@~*yh6SV0qlh?-VqnR^VPi@q?Bl>`dueuc> zEtZ%R)<I#M?~jC=6$S;Oa6P?dOC2i*Df`){6Cp(rHg_Vi+=I&Hf>0rAt!nVW{u0lMDYNN64 zO_c9$JK1k)HGAlV@ExGZmI$=IlyF zty6W7yS_y{DssVEzQt*~?NI(DncRBSh8-b?+GEzOsY2=ndtu{Q+QF?xd11{WYign! zon*B^-e=u)<^`<}A)AW2p|!=xhqp2o;Q5ekCLeV`KJS_EsCh=EHNQl2T(RwY^_lQ7 zE`#p+K7CG`ZT~_yDl7h#t^<_LJPq?iZ~P;M*Tw`!5$-;ryZpND@2q01yBqeB&*+-7 zml!M+8J3`8F2>clShuL{q_j5Xj5K{^P%Hj~jB7SYT6erl{`%SQa65GmTkzUqDN|J~ zx&phUI$L5^HVM@a>@+yAYWrUq9fvwNxOf$;J`a6#K-_zr2S@O1Wps?Kn?j2di0K;h z3dVVGxLyEnX-va1Er5^WqYub$Jr|yLh-T#4=fi(7$mbRG8EsIkq8oKktYP2RRM693 zP~`I&RBDjVXHnVV$!A|#B$?pyeef~~R4=Me#x^3yQ6#g`fffB_jnEh(q$P>w$E?2& zU=l5&wLKqHOHh#WrOgN?qm7G#I(tI}0%^(`^Jb3Htfy=fl+UbtNpo-1&^iQ)C8FXj zhq;*}0BDVowoHWdPhrbEWsOX2(}b;1$TVA|E26k?BHTVhjB(-yp9+qAas z)`(?ZF@IT0BuNZu3&ant2|I2$8fWw-L+>)|%CKA!Df+7I%!Xm)plax=8@Gf7Rz;8j zGtx{AwV{U42EWRzviPeLP3a^X_F`yi#$j5WRO%4af=Qx`jsJY7%T52vi0SOn|0TlIo`9V$7ul5Mqp*v zUHbu1?r1>iC&n%_}7edOSbMSvi~cev*MWm%^s9|&Yt`ID$-V9 z`qih>t?eBL9|e1J0?vZ}hya_cK*6WsfQ-^4O91YgoYG^FKF0w-peE9RkYA_%@qi|I ze}-XJE?7%B7i|+!0*jVtyJi2<=3FPC6ks4=;IJSj>|4$*m4dQP5?ex%;$4|`beDlQ zVmPl=1VfSkebFsIOfJWPftWDTq*9S&vjblM5u`VW<$Zv0!~E;7O(Y@O9Ke7cc}>)S zN#V+9XImttwAMyGA^}MR6hZnRAz24hwkFym9kJ%f#zexYS+LQrx9Z?*pdo^6rrkRG zRbG|N+ZO>Oolh%ZXch8%c1E{2ISL3wUOXB=1gm37Xxzz2oQY7CG{W)kEyGg5Qe_J+ zfw?r%7U^u(#mMB_l+*DsQPHZyigjUnZOlNZJF0EIGGu_T_JH`S5I}&uJNS-GhkMH4 z=ry5|(Q+*;Sf6Ctr40mcSx;NqQUmoaNH#}#Bc*^Kp0XZ;I3fF-Hm?V&(K~ICr*E`x zh`XF-J%wwto;n17;MOqn)b+)+fE_!DOdb?gZOXP0J*n1jJw>gLh><`CW$0-U1K>mZ*Z0SiSnTl<*{_&MZTRW|n zmqk_4X6VJKPA6lMEga1Mg|*QhENvRo+_WrGqyoq)6NgB$9O2$Y&}-8r*Of&? z@s_to+AQ@`UsVFag?v9&Bq94S7Wm2_63zsEBrwL5^e{0L0Y>@6V_PX+dD3Gm?K zFPvc@JBk1XXXh!Lk6cg)GP6!9<*$b%MfL<0j-}&zeiWtzCR2s&@s}lA(g>}!N5?n+ z;I3}Y!b4e-A*xYH>t}WR2kIgn2X`l<4n_b!B|T`i9@%{{$`Xtu9csbG0F%EOGRpcM zxTKI}smmeZ72rfW?e@xJ%63|@&Tq}cpf@R~m~ESI-G#z5|RH+;06o!zRU@?qbq2)yhB*J|Wp;30hkzHO7}y(H^hnTWMm8bjnvZRxOi z>Qv~in1avg`w~mA&Q7?otngp}#6E7Af>KV-dGGv~%?bmi*^ZbaPkZNQ+R@Fq9>}^E znA_p2iy{4-!)Pm<-yZFVcG}oLJoPbw88V~f9anuH_R$l4Is+guAA%~?$pR#V(jx%H zunF0=l#XR<5aCo4n9umbZru?{HX=c#17&;_=m|Ezh|tN9Gp9W&63?7y#j2NtrU(Fh z)a=j$C9K4H=ClBzticMaqF8nJG+|qx?Vzy$!pv~K>R7vCA+Z^CCIGw+>ZwCYB6|ct zOxT63mnsY4RCYvy2O_e;1Q4}BN|A#i!GjTm)%C%-1qc~kbFzUYuz0nk5AFsT^wI>O z5uIBO-qh|iO(CZZfka|73x4tAK!ffrJ?e_Z(ns$F9Nn=IjI}gX3k-u?X;AqbCQX8} zf#@h?U6>z~v{*JA0~&R;TB{U+MO|GuH^ko11sib%rwQt3wFE+Rm1@!PrA6pwk&_d(~foQ1DH5>ydO3E9&IDd#=n;Sz-H|FDF@f&D*BADg9{uFi||&!{9>NOH5*W%zNs}C zQTDai;8D1M?2A}qS$2>gS;tceC(piTL7TFcSJyz0U&wT7rtSQ6W7^5KwV*v>8R6)y zkG9yZB8dL}1?|X5YVD^DR3VTk={T(yBKPc;NF$uAR=q^VqE7t~5Mo74Qd33z0$r->th;Oq;OT`C zXyKqWdi79@K6p=sqYKdh!GM8paWuIl;=omT5K8+EFbb-j_8s{aq&s<+dDgc8?yB|V z8POAj7QsD{ZcCz!RcPy9un~GoOrR;s-~ZI!7T`lxlOC2lOe~qQ~HNsTsq{;XeVke<>000(gP6NeP8A&JgQDe$7OVxCJ&>=9{**C{q8SUiMkSrOP zSsgup`Bq^rbkbCPl^GZ?m};%#k*u4AyQ^qr*RcTQFSuiy(MaP z6BOk`J><-1;iJT6pMD4viGUBlN6whUa10^u&D7Hc<1PsgvDLWK_P_cn+Y@*XU7;h4 zwkF|%xxqj}Gl`$prO5qh1!54kYjh+w#!^kKlWPwCq)S;bDq=?n&{vs^wpc3z@BpM7 z7M%r^X-m($zcQViT$apO5k@scd8#7TDps&E(jJRPx}zJ}q-Y}+FmU0x7DyI#+UbL! zwSu6^O+;X}Dyp0f8c?8sMkgoYjMGk0RV0o<8B1<)APi1)NLqVUy-T94j)So(($j2{ z4I9ac5l-hI9AK}q-nI=DI11fLTVjY9m#Ljqu}-Kpg5FVRODg%nM^h|wq7899V%p$HuCNwP9f~_7ONvVgO<7KPsw>%0*v< zgLad$p8zPXDq(;4t1;m_dgi=WONtgpoeV&MT4-B1sK+?v7z};h#W*U=+N^+6uDd~gK3r220ufk@kdD}T z>wqmU^iZZR2)HE|e@$!FXoscF)(0&K01}oyHnK2?j8MvsGR^h47)g2ZLeeNlXnE@p z;161Kr{jr6OKlqA-8!d|F#e5F&{I5$r6%BbdLw0zw^JoN_38@FMhOQD7_Y3=fIir4 zkUPY>K3w#hq8XO$RKOUT*#{t6E!SGU@-%|p?36r68e0e%EJXDY$s!ilgUGs9Oo3=L z%ys2h5I8tp0*i5oy3T-PjDIRZ=oosw-O&gv0HwzVQC~1AIC(4JnS*I%pIbB|u)$u#>MZD7Cek_^4i&went`NFyYYai9%{*+YSX zQi&u54vP_c7|?OBO~HXV2m}&h=jL2hqcQ|27d9Xex3e)~5zfoazD8)Gy$W?{CjD)Q zgJTpEJ=XhT;M8I$+d-&?B(n6@Bj&UdDb13W%XxK`>_u#>AUvhJi56fsn0Nrg z5)of@GLjaA9_WKp`~Z<^jge_psLl_lOmsyM5l9<-u-dlA2W_|a;}kAx>C8k@JveC6 z9ulaNisxC!Fb2sE)P_tS_Ar1AqMXx>`QenMh$bj#dcoqYfCZ5zNgGPzsELh=Z;9z+ z1_RaLMPdiylyw&LrYga0OBxB8pDYVDMQ{AJ}^ptU>>8^n#P4H)7>G17< zD7~v0KI>>ZIkFErEcvqD8rUT>mh2j+i}rL<4iI}>u;#TiI65C^;m*{Ml}k8?`($US zfr4cTpdt+ix;^@9A+vCp1UrCFh(*D2Tk91qp=x5yBJPquC@LLgXV@5k14Coolb5yP zEMcs!t(xIqg3T~WMm8HJ_fYynGYC~~7b2L66dEV*q}MiyVjsMdsIOZ*=)4V@$;o!G z)})&^#VmCpKP-XRj^iLieKl!SZx>tl-A*SKftsB6CL37VPJx$9ztW3gghI3*{E0P_ zDM2j&XB`a!XNQv+-B$za=lc9e$wIPYnTGB*VDt11&`Wsfkr8Y^!9;}V(^{^=?Ay&O z1~%;G1f!sy*$wTIYbhY&Cce)WU^+(ARC(sDN<=q0OmxVx)fyExNTEOcipfNRMZej! zi86I5t5cyQARy@tPDgbT5S+@OjYQK~k7)IlXv}f9JamO7OS#H+wkU_p*))gN`%M{Z zAb1Rc;N)bmMZ|-r_SzowcD%!hM`Vm(%ZzM3*58;nBCtFi0}YuO&Y^vxI0D52A81Il zx5c6-vQ?`S6akUsdk2;dvya`2{9&%v8=!@zj1COLGF_SQ)m zhFO4eMCa$VtZ!+uIn4_6SYhWFHX0z#-qG3yknIWU{lLC5L=U7@!>naUE&;Jot)a&) zXvaoEQsQmMWXd;e3}jKHSHT+QJ^D6)4D$kl`7s}UOJo2;>3_}NRB1od%~`1pSQIVV z2sd~NmQ{yvtsGsfw&e!uvCBB=$jmu778<6nK83xoHgk&-tHF|OKYgJl(v7?vtl#w1 zwK&Gx9BPn{G*Dy`!^b9otf(C8wf0EU25m8K$$y1}Qw&aGf#g!<-S+>y5e;r9CzcJ=LWm$>)pC~hXY$)wZAk14r%(IPJwV4`(Ifs-XCLI+ zg|u^!B}n?$q*%rHQIvxLyx+f)Gv+3oW(E{n*V7@0>+%!3nhk<3exc8vdpZrs9JEQpb)jPnW~Y91a> zZ9){6MbjAMKQ<9|c4IL>qS1y2ZGd1`(L#h#>XyZVRk5d5I|ehqgDfw9;Z=6xJ;g=< zG=;p^Cu`Qy4!wagOWtUBrfSW?mKcvIlJBMK%0p%?-P z#aJZ70ejOO=nCttErh}aOiH(BoU*(ZEMw=IDrg|ykIhv2UiMU_SlSp{ir^Gn;tykU z6h*{aMTxYXh#E_zH2uw_z7;KrJ$)haEILNF_?Dq}^YewtjD@jHx)v)4Ch7j!v!`$q=n&g#)~2-uy3E-068?Wo&_nUQtDaN zUzbMQJ9FtPjmii|AD~5T0*yQK1K^nmx+0`03cvqe{94gEZfJHa#r3ddw+E@&TA$@hNJ*iepx0DB20vrahU-jYT z`pFn1F4#V2&b?hw7bC4ul}VyKQbI|G&g z%+ez4pCY77?TAFJ72stK6gz;dr(j=Av>cmQ><5m&F42uG2^Izz z+L0JT*V_h(gBX~XthxljqX@iqz@nhe+5=0P^BkvX&sUf37H#V7k~>RFZ4AZ>1zPh>>S@FUOWvFd^WN88?IfetM$=`%6@HIrEtr^xmHbdN7C)^UPt{nQXE8ANi zX^k~n@j#|88JRqE1WOJAGKx>ZjecH2PL9?H_RkuJr$IMGu41H!A=Iy59>bBIx(GKmac ziWY5yi18>SVUBcj_J3uet&iR^gAxSA6~RM#>9tH0@?9`HjSgy z?D1&SGP}O7dQ&82+Bsz4It+m%x4z=7gn2sx_G~&$w*<#Jw5_nRmGWpS0l_v+0+f6< zJF^|vi^Qf@!Qi==-+JT%$PGvX|9Y_mcUlw`)+4(KCH7+U7mBAqIW#k8^HmO#B|d@5 zXe%WqpchPJ;nM5(0TTHp5qIXGar*0{T`?OoH+ZT!+M=wZZR9`FZ7K#CA$hQCv7^~Z zc+<&|b~y*vwq~3}6{6QD&k|Fegoxx$s&I;d1TyAxTsb>#0ql;VF3O)?K$giiC6G>t zN?+y@P&LMFdNHZbW!M?#WCjCGVw+XNjDiRfgn>q+D(R;sx07cS^B>&ZmbRCoWmuKL zpXa#Qk}`@kVg|Gtl!Xl#)Sd7)8P;4dALy+&z^BI=OkhPAx0_If2dqK-KrfD52l z>d)AR+rGtdk8?eafwAgTZ(X#R#VeS^T7JxU>#?Oc4g>pfI>9z& zhd~&qPb4OjxycGE=e>^p`YwbmGBIl5M`@tIMu)|8A&$s_Fo1Bf!UQrh1^+4@TM`K7 z)53Z<5n@;)&`LxoSHOBWQ`-q2#0*5&TayLnObfQ68~k`s>j{RX!x$M-6vnh{5R43f zp>(gXF_>4ec|}>Hb}Mll!sQ3Zf~^~rr_PEjSO5y=)I9T1bGnrH5+N?WWf?3(ot5?! z;{5XbmUTBw0Zw{JTeJ)U8Rw#4hn`)3GxDTi{Z|`B<}=ZHf~J}%!jPO`r8}$+mIGjz zg(y$DI@Po23nQr&^KGDhV>E?DswF2=Zgz@9K6g04j zLfmQScH1pOWNxtoz(Tyb6*bB(jt(#^2ZD0wuFWX0t-L0;KI^pb9yCCawmflLJ)wV)s#{lOqt#F{PttrIG0#IuS zNX9|;fQ^rKe_O8jkV(JU$)IEhgE_WfLW3xAj7GA9!<;WL)H~Vfk@QA)c8Z?=eJhdb zz$wrscLy}V@uIhPC~ zS#vsMwB!gvm72sv7BISXXTceUJWfu)u1tG6c-KVZ!l+qAX@_S%;Ru0(u`Sy{?X*Y1 zw+1^1O`VxH8pDF^z)qeuIKAEygZYlk;9o;25%e6bQ{Zsw4AOWZsMNkCZl-e^xQX>& zwxG(%2#Moguqw{QNSI0b*=TtwNetcoW6B;u)$I-N%ATicpW z^h7Ot!&x}^*2dy?M)N-C!d?QA$06%pY+g(|fMHVu;3TbGvknkwhA9n#$AF*GjoAUyr%s=S{Tr!PYysa8>5UtYRrhqj1lAj8XR52$ z3s5ya8$YTwbnXFp+rrYP4M#^`@_X*+=*#FvJv#bwy7p;DM`wSp936cHl^TwY-bQ7I zcXV`LEi?A6dE2aKeM)-f6wEo#5Y1`m#rTgI(Ttr~%sNpXePqdTvktN6<}NC|-_Uah z>08>N-%rzx+H*f+NN7FxbG7H5r&2@Dy+~z;*K>W1YqawUAz;aRN+~Q)zzL494F_pP znvA7xT~L#8+ExZXH_QBPspI<_x?^3AAtscBoONvlp>%I}?WJcNpNB6PQ4e<^*(&=LjE|IcHn3hJDaPQ&wHV_NQ4)|BW@MJCrq zHabLv;V9Y){?uPSjv=>`##fbgPB3DVYaX1p77AsXfVB+163+r8jhK68mCo4 z!D8#=>^W7=W>%uDL9P01;=Hv62f5Pe+{$5@!V!W=U!gcoak1)<3U5Oc zx>gQMQseaHhd(Q-oK>OG(zpO$}yy3Q@(_rArJ@UHvh$QlTj z`|07~t^G`=Dv~JD25pu7(T@2|4oE5mYnv6f;MA_9(*{Zk58>YR+*kP6AfGR90uV$I7_5!qx(id+I+HjxRnCS-fIN&H>}I?>`KiIifq z@^Zk)yZag27#%bG+N1ZdBeqlCE>SJLql2{4|70 z4MvP%RCaibOsSnLy;t0JHIjrDbT`L==Es7sVG{&~gLlwZ6^(96SbE~2&UQLwE?*7{ z1~(}ihJnSxloxve3|a(l19mRtTlk7k?j{Dxxfq%L)hNHcdxy zl%72voC;~s!kE0v`j$mADVQYep?Is{v#>O+_^MmmBN3Rai!XkiOi919W`gfCQIt$QarU(d1+*^42#YubNfQfd3rXgUeJxq3wG09($=A z^M<3X2ywU0#|%Fhuz6}(~4g?y4=#SU_K&DF;7v$ZD8n=^RdN@A%G~btR3gmIp)>#EyRh# z*4g3%G=@@Jobu=wF2E_DnQwc{r+J^Uw@lq7E@Yj4INzEw1x}{e5Ho#rMr2cj3eM|` zHY(`~^Ib+ZC|E^A(D<3(V>gFTrXlQ2bJ!Vc3j!$=Vk`#SrpIBKX|v1F5X4Z_OP;JA48EV4NRu1Mb0Qrh1xR0J8=5FJ4hMA*GpiL~RuGjqrCT@gTVT_?g5 ztU?^3NGj@>XwJkO22waiK{5Njcq;>@SmnqPo4$m(P!}ypH>s>=WVyGOH*M$Wg&5fIH8+B~4I|H#sz<0{Vhr z>8H3Svc9s8L^BJo7PBeSfASl!%?9D3B~A0O2^@#TIP5j^EW!!u`KA~wZ-w<~Bs7Jo z#dgrb-L)zaZ;HVPn1`ev_=r40MsIdvk=7!k5n>#z>WBM`R)}#Jdayzay6MQ!p;{r< zca;8m)(XIhuforyI;_S{eit9pLMcwA8`TO?M%Otj#C&-}XX(()0xC2ZAu6ft@Qe`t zRneH;MhV}1$SN%F?T;^GDgL2eS&_a^{-QNDW(4mT3b(Wj@{@NYN{5bA1Vfga(KQB; zf03|{wq)jT>#Y%v)?gAf3F5~>l1LgCgI<1u9?YEjOp5yB{dMc*L;#BnXW z7^2>3>6f=asNLaSpw7Xh$7|D9KsiX)DNkg_7&q(Ol2QQEo67Hpai9 z0XY7E{K1CO;u8)nn(d@y>9v#e1NkZXjy8~=p&NA|Kl`ry?j7MFnQu2tbB3S1#m0}r zPFrk-hi74g9bKeRBGMh_P%Q3^zp5vNN{I=IT>EB9$<#xYYeQ3|uN&mr2Ru1GA%=9iCjHgesQe2tf^v%Gu$zrzb#fK6uj>%cXK5PDYM&G&*jS zv<+4(p~FpV76{BiI7}N#~ZV_Tw#9G@wO7oXUtfbk{glwOqK<}b{H z|F69-kFTQ0_D|Td5M-4-;42ua|NQ#g^76cV9%(#piSu|3L zBZH{p@IVm|g21TYF5|-Q^Yiyc@QEnu;3%Sw^VD(hopbu$zTMT;H#avSYYobRcvYk31>^;NMa@y1)syoER>zxc+L<$2iCfU|u0I~W#xfug8yBPT3`#YcRE%h_6_WHSu$*}3C*9kG-qg`jOq4MCPgm0~ZjumSS4tlg-B-OP21fub&=32ao z@^Pi4l6SxWudX@~E-1|_s^nb|la6>S!e+~0C+_mR%5wM;yXb_x#vv?h9ZYldIt6~O zun)mjzbg_9rocjQ%eh4|r5Ghec0LW#gUdB;a_5!g78Z|OR_=WYL(%0}JF~^}AuJibje7U-(8>R;Ku_VIKa5-g8Nwc?E@XGn1w>VX+2| zFFCfl??(;!3Ibz2RqqpG)SX%fdzluLKi+evc3Lv{pD-GqKfd6zN+myz&~N*f@U{l- zsqoHbu*SN;T{PcNvE&WW*-#Pm&4x{0&|!R?5xLxY3lm~fOQK$GF_GJ&CmXD2E(E2X z9d~IjNu839F*=`m&ij?XKcjT`dZ2&(MDLV*fuT~Tk0OtEv+^wrDUzlbt&6@Zw%Fm@X;`;ubH z&0{D~bq$A5e)%|D!d`;QFNm%~6o!Izh&VbXMihhU^UVh~M4)B;iA>(Ia8*C5=2fh`doLevV; zX+*6NT}IRfQI9v^(iYJKMC}l9MAstPh^RfHh&SQV0nu_q9T9Cp)Ctjth&luE@Hp!3!9tgUc~Q zI8MdSA-WEc_Ay+r$H9*y!WK3E3{kHU2%CQb7i<&pL5Q&C<%NiPBRYr(OCEk25&8gc zc^)o(Ply{fX&o93JR#O@(zM87AX!(*XNg^#w1pTNwOM1~v&8kAwd=xLi&Yu19mUGc zT5@%iW65-!MM1=oO zM8x-Vh=}ihLqvT49ue{V7evJOsG9&0-`gT0zQ-aWzV|{zd{0J%eE0BFghcr9h=}l0 z5h3CETtE+mg@uRVpHBS6C?w*qKt#m95fKr810o{+J&1_-4;i@%lsi6ATRXa z7vsIe^89TUibMQ9j$26_0S(Y~@Oy}11N_V7ztL}`*VWc(JQ%&tsjBfBekUcNJP$pV z{3h~V$RPPm8${$cT@jJrBp@Qc>5qu~W*8#!n{kMmdeAso2+48gAR@=fLqv{Kh=?3# zH6n7H^@zxC?nXp@Q;CTDW;-JCn?E8VzuAw7{N@-U@|#!h4fA*%=UogW$2pCN9OpbD za-55Z$Z>u^L={D&jey8+Vi1wvv`0jK<3dFBL~lgoE&~veyNpCc?&3*DNd7Vd5&6q} zMC30^5s|;FL_`(EO^C={ZbL-wvJnxv%Y%r>U3MZOciDr8+~p7=a+enoC6fQWiIDu| z{~{uP`4EuBUt*eo=&pShcbR!-bZy-Qc8>y5c|9r!f2nJC@j&c82dv{t#_lesKz+Kq zoI!-{;^ChnB!BrD5&6rHh{#_W?*~Nw(gG3HGaV3-yL3lH?vjXz++`pla+gtv$XzBO zB6pdIh}>lXq88+T%Mg;ktU^Toax)_Gm)jAMzidK8^~^(v$Xy;oMDFqwB6621MC2~V z5s|x`L`3fL9wKs=v-{Ei$X_mCAom)3~LUAiD5cj<|U+@&8P za+jfq$X(J9k-KCfB6rC_MD8*%7a{q}azx}W<%q~%Jc!6&?m|S>%l(MRT^>P1?((Gg zew#MB_0w1p{|YFj8zAZxG2vk?G2$02<5T9)?%TBu15WxL)A-u} zDMtlZzi;LvTECn>L8y0Ck2fRmQ~|UI_;J7F zWq>#!V)`|Nn6qR{taBEUq%2U9t4X})JBUw?zA1M2l0czu{xOI%J_9X&g3q0YOL-o( z295yK_%_3G|iRiaO>)1wDy*caR&yQ-|2T+bXSa}0^t%&I3@~MT(5s2y zH@Bk+sl-I2%mDnBqp%eEqm+#_YXb1yZ5#EWhzcQrUUC+T^?%gHb)$E$byUupC$v=E z6_agm<-MUx;w#oN2Zh4}Sgutx9XoC2(4i_{4UKyvRK#fr+#7N~=#9_v>lCXxj!e@{ z7MOE6p>mER&8j0DCC!m=W**?n>V{@~HM|SlAKo6NqS+x3D=92Opc&r)Z?lws+l|tX z+F?!3LdN9Mk0k2SuZ5-IAa?K7(q^cb7fI_TU9ebEQPLs*Bk2fToCB?Rplb9pT4uPt z)%3_dZH+y&&mL{3J@msp+QphSPkwqz8|FEUww6f&^>8wkzDlW4M#+?EkLsn;1Ci3K z=nW|Jl}x=dT=qi5&lx{uTK}MR6<FrhH(QFQuN(V{r)Fu{ zlM_>tRpnCvc38-PRvv~ci=oPMi^F@hLI1xorR`^dn4*+61g0=Zwvvh>1g7vGeD@2aGLZQK{Ypdhcax1T3o}PU)=E|$*qEbC_Xg#aP1HAI7hkq*b>X^YR z8Up@U)odV15WK>S4a0R8E`5DP9~Z8m5ZjMyeX~`)l@?=@T1p{nlv9e1gWifzN*&9*zZo}Y(Gg=WnA>GOt#DbTCY(-?8GH5?; z;*@lCBO)~GiLJ-AfmhIKLjzh(DQyr|n_7of<9*>}mgd8sjZt>`1Qn0-bmT@nNgTW} z#_R~<(ra4#nl>N)@T%53HCJUEV^}@#D01`Hw2AuA`UqR0Z5djZBcV~`=``?kmqBY- z*XGbl2&9I((SoNwv>-=9T3Bw;0$(lDOu^T8Y1gw*Y|(9eQ5 zwZ%G1<_2bo9Eph~$E_?;*7;Xn3&-k13vwhTmiV;556CR}!e9w~u)a^l5|UggmUMbY z8=88i7W%pO9c_%xlEHylB1d9k$$eIqELOD)ue=t1tPd^7k(gNG(*nOFv*ZqgB{X*; z`(;IyLy}-w;;Gq(Tx>M9oKm>Lm0Rk{b#eSCOijU#e^oT=f~kWVaV|FgA8oi!oRq-C zkz+9tr_f5AB`V@v4aE$q7sbf2n7HIq4DSmmu{2-)pTQ-XW|pohaYzy@mulL2nev{N zkUA?=1p#rMdQVH!i8C}XapXu$#Mxja4$Nz}_eHO~7E0?w3vwhTmiV;5xy+LNMwgT3 zAN@(yLukwXLb)lVATMMTQZ9K3*|(AQneu-9a!Z`C+N zc8irhOI7r_^6J^ERF525&+5S;GM{?*A7oxVZj?SW&+mrO&Q2 z+9=OklHy23@E!Ads@0TI$BylPVisr!7Lg;rQ0U{AC&NBd#6&Pq;9ft!(sQy?u2=CZ zST$kh#-$a)(j+*>wxG!Enjl7>(NaTF+!p~Ar<7hD#qo18^D2!JjpkcEhAUd+ZaYZ= zFfYrBr3DZBJE2WMaJcxN9>LGHZ9twTbtJz3c^ju>k ztQ(|T8G{Hv7wkyb`v$Ai$BuRQgkGHqd=@}fFCCX#9;4IcLuCt$L@%E3M@1N89)YN2!=e0qec@8G) zPo=j~>S(f^m@{%AL`s4K(>Mx4aiK2a@{wN6y`Q94I-2a>PlI)#-6j_rmzdIDRWSrI zj9m0|hD~Q(>BVs7xA^K4?bg7e3eSs;LX@_^ZZ->_Ov%GVw6{g2wa-Q*ppVsU9;;%J$Axf89^lxoHj)C<0|y zj$u6_C+9jD5VX;9$g{bb!89!FWFh{Hd-OH zSn3!qN0(b6B(XaSS<2c9Ir5$My1jnmUu*sBp{M??m|9mA_q`UUn0lM_5AB7TT0Ql@ zwf>%A4p!H@p-QQv)!#AN8PFEi6WlXlA3DT(UN zZ6LGC1=kDH+$D?Gf(MG%zSEA{jd?Xqydt29mC~zh;@{MziTNCOo23DC(ePhFr zg-?@2?bE$2lccct)wiZn%#;^j{iJoav!TO3weB_b)}{Z1IV=x5m{Om^qLezCatvmh zycLn7x1!MJt)7hjwicIl(5T8+u{E7CHcdUxB!FhCQ*1OS+q-tFt~L97K+P(pS4Xpa zuT1Cl2A%bl@Tw|`Bx*X7(*2`KFZ`?xswp=|{GyHVeBhwL6zUQyrH&fhV$>vv9Jz@? zA2(|>s`S8U=3STZEu>ocelhiOkhMw16MoXCk55Ta^@pp|zmL{fn)HQ(@K(ZhrUh=7 zc>8CqS4h@q{5SA!MeAC(hEm!9tkDTlU02rNKgo{L9(OUJrKPmiycIS^td$~L*%sZCCNlzRQkLqPltV!W^{L4MlP39CNWZ0-a^5J{ zX)}cwRWpSo4soPkCf`&36)2b;OIGd)TB|7nj7b>iCO(x6%hTR)X>*(dj z#D)kK>ybmNF_Y1-=^ChEgF=Jw6P*%{gGgCmrhNwCVfR%v;s4jz;=bT)AwQ#yB3WO1 zi~jvcmSPX>62<<*9{Qdtv}#i{dsxx29~Q$D9f)&DY`gu%oBA=u`rB)r!rwJuEg~&#LU9r(3I{OK8J(+n+txhPiB^Rju2yL5f7= zv{U8zY&+E}T3*X;Q@p}8RHe-69ayX_72?(o>|T3lmyYadd+7TeRf@l>6HBx|J7&0w zDYtfJZu_$uwL76w9{SL%)t? zJ?x>~yRkd%p@+LM`@TC{<5;Qf(XC_IgSJ4C=u+6ds(%`5tg!H_-I-!N>aZS4*BZxC z?a}S+!M?DE?uuuR*h6Pu$M)GnJM?7TY@t=-d$N=E1XsCwu~d7oSgx^|ws(lPHP*YP zeS`$YmU`xV3B{wLkD!nJDW#5mgd4D^rB)^)$5ti^eU)xadTg;`YHt?pp$Li~*-jBu zw8|}+Q?PniN=pAhN&N>5N*)Ls7)#cHZvf}t6@^a||E?%t|6DHqT~Ux48em1y?W;f)g;LrODvAM+>?>MP@YPTiS^DgS zdIw}Y=!>>qJa-b1+yfy=5IqpFEt8dc0xqM&PD<3w+!f{SLe~r&g!0yPQMUeUMWkzN z@r^5Ti)uJj)r3g7Ig8C7G8JhM$^gL))0yKAT>4tSea1#+WVlfg=S<5=Ojhp0 z6|53bLmbYg6+1K8@&=^LRrRe*z6fHpkTuWfEz^dfzg2OSBsQ+L0j)~AREj<`*zD=5 z<=fFSV2iy_s7K73I*TpxY(!<*TdF#1xKip^0Byr;QbQ7vQ~AJA=yRucN&5X`dXN}Gkxg%~V;bV9G+ZUD2; zCi(xZnp#d0wIf*!hU{rHrU>}r-MJY8d?O}oG3#S1HLFf7W78F*rmrqh4Q&5&3Hzt* z6{6WvmQ_>Vy~vqs$U{hyQ2ItNn?2SuI4QaRpux$0-w0-AduF(Q7USHx=_&{D8KN3> z$6-tRf0w?GUrl}UT{81uHEIw#7lC~YnwML4Bq2+53%ud~)?j|0JN4I+k^*s06Bl5II&sD6DZ66uydirvv{4DOSE)EGP=L zeb?Jx)67eQ`S{AUu72|cwjTP?Ts*6NMM05Ev?ye=>{hE6TekZ;kS&$ct8B~Okm5SC zC2s_8vs6!)jqVqn!gA(yg_Dv*U0lX#Jm6TII9tlvXVN^F7~AlhcbaTXPp`-=VZBF> zQ5iCrEl%`8eTJC+Ypt7j>JPmJ4E5JAGi*t;?7Ah#DF&CbxM<4U<2WKAJdoMRauF9m zdsj<&ORj?Q>vqF5kPBrKG+Sy2`~*YuQ+Rcc3AGc`HXER^G(oblz_A z@wT~wGE^(9Dv^vKbdB1*xN7eW*i@M4=9z012_QBpcz0dPJPY zNSs$y#34zL#EBRON6)V*Gnmu62F!_F&w8Y0)k0M_t!L>vb4FUNfVHM+Jw2BrQK+h- zDda@WoZ9FkfI3>@avPJ+2+~Jkedt4uM4=D9Sfo(Rq^`2U2YsYWcRGmHJt%i`*%0*&bD_&g-cjMTOI_79!Kv^-GoJ-#~V)xv#kL zR8hrxwW*Q_ny53X@E_&!=1rr#q4S3$RlPZqsLPwF_K!N_ihX5`Y`|;gl*4vvQ;Km- zSbA=O>M=25Bb#n7k+yGSHC|Hx)kao6WCHRigtA4@hnpcu{f7)1ILO}#4eG;9gvl|p zoc4bSpi@Jo6O0cx4N9l^S5v2aHpFget)JcpCZ^WYI#{9 zY-3p(LOmy@RkD7mzeWv7rB|>$y%G1bL3)d;kF5f*wAbZGOwEh6@JqeL1zAzIxD1Uv zFd-?7{(?BCx_ZrYHh251>DN`Wqdrt4N1{*-7c!5|8$1fbrh88nk4T~}2@S9HIc?*4 z`IaKizX`*v2iby}eun<&L6|IjLZv+8lxn5a@te`R-4%cs|#RDwCs}HqQ2Sr07EINAN?I0 z<7o$3HyaWqFhAY;{o{ zKy}q>ZeT4`mmE-aO6k>69oHbG7DoQgU}PU; zZQ4FNSbR;(`*l0mD9;QB4eRqYlu}0xe`Sypks~=#=p$#)!YVYK7Th{91Iv<*K1Bk~leG;Q1O0cQThgU!%QK5nI#w8Yg$M&Z)ap1`hHw zj_a`?KjX-ePzzR{piz!qAf9=Qxoi_O8lblRTp!w!BOz_Ir0FcAEv!_Z7ptCt`u+nK z;OHh{VOa|*`31PiEvwv6$v=Z+YP@R?lQ02p%))l@CSf_Z~y{LXy5~{^@B+*z;GWNc+K!InsQyutXB>HVY5_ z3O1NA|MVlX^b6^y@$*fQ_JtesFSE_Ug_7__vv7l1=mC};F-u=IOF@{n&=hGV+?XTX zZ5AGsgi%XOzibOP=3n;l3TF}T2T9USZqrZW;l}(^zRV;ngB!DOSUw6x_%7DZqx;YW z3TdJ{*mrPae*EbI)4LACjahi!EW9WQ4;Gt#`2yUSf7$a65PF(>Bkc!wX6eC7kj8k0 zFTjmic>C{7!cA~v79KJSUzCKCcba~gy)(>X`RU*%P0}%NV}5VGSy&P3A3Lu{c_>f-7L0Q#(4;8Emmd3b`&c&YsulQ z#ERW)xRwQ)+*GNNBX6#Vaj$?6l(5ZL(#oP`m3LI~sXnndwVSyju&CW!(eD0tCtVu@ z((#70(;k);HOaVLxrcR#nrz%|2B~MF?-u@Vu872$W4>6@ETSkBr6iTErWA~`$Rct} z7W;lR)*@+9Sg40)65m#T#R~}weLOK8;V4P%y3vC=8HDRBI+!*EbrOg;}g!Z2xCgzdF5qgMv}|X z5*xn*OYOpoz{?K2Y{AQ8c=;_}_TptfUiRSS9=tq)m)r4DiI>B8If|EUaOueZfbbw( zHs@7DEGb-CQ0OkLY>}4av!=uFVXV`}Dv*N2~*f98~?PJ55oQ0>ws<#q4id*-w zHW0dHA4`CLhxf6ey6|7865>R={VWzjQ}(moQ7s^Q>mUzjgnK`m4582LXNx27MHL<5 z?|<9fK_nkw1N9#tKbO!?JOsD!*gFSUfgalZ(}ZNP;#t-mLN`4NYede9bI-CFy6~F| z3Ejl3gDhTuW#{<&bB}cv4;^HK;jvQ(*?jnybchXJL@`FiFD@v{Eh~V2T)CV70}=s^ zglD^eAC(i`DWMdq0n9&K5i_Z%tfY8J`C|GFrr_XH*` z9U>iEQ$@LX{VBh)&u?>tzv`pTy%{W-()w9 z?XRbyX?AgOAy|eYZx&xhcY3T9(P_m+iwnz3F-P#iOGj8oG59cRkw6bOk1ugAb(gq{ z7K3Gt43~2(NGYp=A7(uv>dl8qUy#bldJ0&)IQ3yT6Jwua?Lj{GIhF$dDxPEg;hz!9 z*nqL1BTy`X6e_Me!jj;fsGw`2XO+53Tv=}S63nhxe}vTYg#Pc%Ba~E#JQ1GndXy!$ mS4S@v9A%!UQTfC3N9L#Ik9hLaqpVr;;|H+IIs+yPB>fLIQY=vb delta 290223 zcmcG%2YeJ&_do31WJAidY=96pJwO^E2`%(q0|5dG2qJ_UmflrBilQJvN`M2>0)ikl z0d-N4CW<26iedp3Y#`VW6#1Wf@6683?q<#7?|q-ohbQjb@9F3EJ9n<0-YVR9VyjU4 zLtE(iMnp_;TDy$IB4zBj$-@SZ8#iiF=CG*+qbDsdlE)NG95r;@w6U2Z$4;I&ZeQ=fO<_T6uDhPZ#d^6Y$PsQcH^?407A9Xp0l z^y1|yMbR+!VW}DnY$Vx=uXG9z9zABDbIQ;W!-_LH#TK9Llv*6tNiM$HDOPB;G{0`~ zz0MiMNu8?|59!o_{)M|8!`m0X(76`G><*7D9+?{jZ&X+46Sa7Mr>gKoenk7ALgeyzA!LqG9B@h^oO{IcHPOr4i!-hdSAsz#pA$ zF~T5@Pws;FZn-vxFn|O5xq*?M-n)@&t0v6lbRk`luKx!SiY{jsC!YaJy4yO#dtFea zjT{=5htL;4G*nv8p=-FL(%!bfz*WM1_c5ozdtGe_!kd(`38a1;Q4Lz=*($;F-E1}B ztGPm;@PlYW z2BLb{VxU)dTV+9o0_0630!zEwoI+h*9+!{t`}{Lht9uVyB>_{2Do~sLNdjg`D$yqBxx(SkC=hqRTF#Z8_&}A;|OD>H$=%VhRmA!3Mgi3I;k1Y-o z`=Eb%_O{uDK)7_7Bntv8?PsfHbGp%RjlxqYyeYKkgHf)RRa@_RGq^j^JCvDWvmW9D!>P&K>I#mSNJj^yw*jGGZ zaw^>IZxh3!lM7=C>tNL`4S7%3ZmLwd5j;52)>(*y{PDKz(3(0$G^cR?)+ur( z*=7n2Ik=V%uE)Tk?%zK`fgDg7&Mqcu@qnRnct+u-!dOF5bYS)m0X29d92HzxX~6Qr zszvT5+4(?m!Q9ly!t}yhwAodVG)0%xGZ2{HrcbsBf-r>X0byfpAwfN{FDZ;Jo^v}5 z;&a66&}J&ODov-_x?qf%Y3VwTsa#w4?@4fEJm!mI8ajFj=Qw*DI(ZSt)z;}WT~s#l_%wt_Gn1A{o8eVe&f?%$JO!gO1& z@ClSfY@XYwp7e3$)^`gElhC_02P`i#cW&|6xy8FXw}QfC#H0>j-BGC7-A1Hn_f~vw zX(jKT?r$2c>V@gfC~VmEfMx3H-VOwo#!Yg>Vn~t$vcvMS^)jjW=0ZJ--48=;Jc|c6 z5+4WR66y{`>j99sK+K7J1zDu> ze&6OCOhG&s7B5VWgV!5~p~BGOrA09TDb6EMFi&-aXvr|h2B8hb%!JcOUlcNN*zlp_ z#uSVkyWDw}KB$BbCO@{4?CZVK7IMAZlJbcVkbTum~2_;S8{hF1N z+9S0mHcK6I4ENz647X z#MmmYB9a=QselO7vbg)R4&r=+A;?i147!_GuY)HDS^3p7#iydMaj~sF`OUwcZPp_5 zn`S)+c<6};?#=7e(*MO(J{(%|^xh>l{1=4(D&fCi{1<}%LS1{8gq?V%O2BB=!Rw^LoAsH}A<+No)|fYymZ*YS72tIo$Kj z;yKG50nSE2u(2tLiE558Qvw^Zi?g4@H0Mc7-Bwr3(Y@;i>8-$Wqhy# zv9TmXxJ`SBh<46648OUjC>$1VnyHZ7DVqqM<|%NQd1m z#io$5S4eYU57E)+A#x{$3%osXIA4IWc4B2$n^t0WAcz?OYH_P&(JLpBAaRNbTtfxk~9v~D}f;qUhV6JAjp19 z%?kVw8zI=xL#!G}-D@edMvZjc=^_3YAmmYdYC{%?L1CuwVX{ULXC5?q zKwKpZgL4mvwS|%J&jVsrGPn}!ZlQFA66nh4Elv*WU5!}JQAVyw z1;%G!(J9iw&NiL+}vsDni5S24qX70^L8Y zhl+EtjvN~*rpTu;N_x-gw85RBVuDbqIDfm33KI}aTlMlPOn5M>Flj8c!r1au#^i#* zqlbCs*HWsf!+Ea~2*br0(EA9wD!y(&BJ3INj#53>&%?zLg1ug_M;*BWg@xiYp$VMp z7?2U6*}lxMy`C$6q}W0r^@4eIT;jyYWEJOc)?#adWT~7E6D665EF)%DFa_ZV+rF9+zhK2#LPY=jVyV z*lZc-9FEp){G$Rk)_fX6+Aq{Aq^uPwu-LfCu#pmY*w`XCeGzSswQ zQA6X$%Rz_#Dd8gN0`W1r0PFU~3afqhhyGg(JK6Vpo5tF$Ll)DXH%y}h9;WTrOncd? z>|Tp$7Z-|o!j~pxFZx4oFB0bof0)p}T20&guck%A&x^!Vd(|+n(4{>qw#HGyoW)}8 z6um3oY#2x>JPfQF#$y)|X2~{{A@$fbSd5jtIc1won)m|>OT;0#D9wQR9H?ic8pa|P z;;wc4XECi~v`wWyV?kP>21CoGqAfU_7u*M3mx{e2{-J$CZ0>r)mccmGiLg1x;rJeA zR|}{Ee=fzo;#n#?H4q2>3t`SOv8u2TS_2OBcPHuLo zeu{+kAejxip!-_H?+@b(N3+(76NC>bzL{{| z1bT3t3AA9HI9>ROGkwNj`n?H1WsyCn zDnyrv8G;=O?8L`d3@6ck#$wST8;kK_ek9!3AVya69EKH9iyY1%XtEJUT0w9Q0I zhkVw$P)keO1sgVrYH%Yo1|g^?_C17mu}$=jw=*yN z4^I=d{#oOYgSn-TQnmFTYxCc5vshD@Nu5<2zSDo~f`VdF!wQ8DZsa2CTURqbKnTxv7p4>3;G`6t!_KEQV zu9{O5nbzM~_4w9eqkS6=_y{^7KttavAMJ2m*d|UENR$MvkBSY21jsHEy97r`yzznA zLmW+Qm@9gDeO4|+!P*^S8#h%)52{1M94Th1emYh4U1B3Q)ff+|OCucdCMx)>6w|F$ z8P?M%cxpG!=A)o=x0o$dg$et_B)zY-*zU^OBSr~ilV;6!CV~DeRi(;M-RTI0Yo%Ck zH2_R2#YOs7JH-n;iM3YT$GiA-7bbyL?DQ_4x?fDwi)VTihc;ts;}%6M+su9nd@+?*=s)IqBHQ!N-R_(3|4|ivO z7CrTr_#3vPOv(w9l%sI(ZLywS^0}qNbzE$qm)x+FOn3)lu5k;1OHbg&1=H=Q<^{-l z){#tgJF4k+i0h_DwwhAG$kw6EwH7yBwFEasH3xV939QiVP3SiM&=cPizaiS^v&*SyQeo)OX&izk( zfJ-8{uXtN;&zpu@!rv&|9R7(PVoiO(gzo7No%WIVDH$Ek!#~-uB6uYq#EpgpAB%O| zh^Kuantg(P(0D-aJG{$t7#wbVBG%H&gPwfgH_=MATT0+-%v`PH4Wq+q;Qdp3P5elPsO?YU!O@e8O|vA5Dn@Bq_Knx**Yt*f|Sq?N=QC859QKA;;QVgl^^ z4u=UEuAYIzN6o$$>*F7$-p^b;J-VIj{~q0}AJ9t=Q;s}h{Ua>l?HgeZ?a`cXUy7pnxS(EX^Gf)f*z(M2eN&wmmdn4WLdpTjk=j_LVp`t#iDV!G-1DgF7K z>tYSl^RL+R;3B4QVO99+m?H%)R0*ty5w_NB+b#42AqZX>hJ#_d{Uw zO^iG*f#SHpG?@J}cKoC=bqPu+d&g0W=A}lPWuX;+#ZFr*X={`i)Td845^3!vm3hs) z$92?W*Egbqu^UU7^Vp55Y>8bVQ&e9&>GwPK%<~NJTz}xoe~2&QDh2Zi9|6q9s@IJ!ZGp*lkxs?9#_ zs0uR=Vv1`_ahQV;{Po*yF_o;lk_dwsagLLRka4`b+LBo$03rR@e#E0&ww4FS=$aIvyaU>qX?gs*t}! zY|C^(vT1>wjQQ?GKlVVPP1+$O!lg=54oNdH2~Mo4Rln}v@+px9YHk9B>Y$=1xbd|k z%G}0l@E#_(!L#5hp9g55Atn$iGb~t2$3IJhrEC(1Gj&`Q*8~4Zm5K$PJd1QM30Y(z zr`O{?pIN2HorFp)$rcT{$sh7)sPwvUfV=4!0%a)|e-cruqd)zaKMg*h`)$^BM;xuc z8r2WHJX9~oURMc|s(|z+?{ziUT{rV^S*oQm$1TqBveX5C9gw9A{KH)HDnd;g23FIY zigcLNjpWs|2`8@$dsNH|{b`>5^x<$R%l&i^dm36dQmfL{;jkiAmrN5poqiHSQo@^e z#R&M+F2&OyEax&KEn%Bq_20vGFGflt>yeIzZ4IZ_!?ucPqlfL`%2GY@vWDF24{5I= zoh2u^7sv;Zyp9a4Dpe9r!icI;9e3GPYgzS3DcN0i$6EGwq?DqU;W6p5>Qa}`le)Je zVNMk(64n8))S74^p2323*otw{v9x`}V&<)P{n>CbO4^Bghh>RUj*!dv;IF&YrJDM~ z0s6yI2ex<`a=iXCXXJj=VPUMxTog^AN2?B6DO78ejc;-8%om->Lg&iE<#Z}n#@aJ^AsE< zuo)~Z48F+Z;ZWgbSab}na~gwCxRfGkYgZbV%L!7V&OgSxctIk1OQX*6E^d${Wrk5{ zD+G3&jXUsyKZCwa!tnKkrL{18{X94Z_l(jS**W3Stg+C5V?2P!;8;ymTq~aKT|BB5 zdPgfR_AaiHjLF_JitF1wiUmAa+alfu8Fv5wQ~H!O1{14Ws^k7BRvq_FkJ7d;yf`|6|AUvUUGUP`aF-E?kl*+BOe z*bOLqE-(T*G?2#Ok)Kx@NXgcHrb_T*11TPlpcm{4^s&!m!_iRrXMQ3aY@aEGo%snJ zGH&dUVdE!HDH!d!*R-7K<8TV_b3@5V1P4ExvoJ>rOSn;;Z-!xO^M~mu65r%WasGwJ zAakVMnG&9Inz`Jm;2&ozhxI^RCjQnAqpd?h$SE9N$&tFimyM(j*m9y}84;!vYZQdq zWWw;qQnQ3E$g(JC$gr`KhfQR9Yvmf@eaQo6Lw;9!g9o4q-0 zrT#b?)#2ic1|*IWH6#?d6z#6v4%^_yZltu`KsJo#JI%-1Nn7yvqRtG~v`5*wT=otF z-cgfHI!LpGp>DXi(|{B(BKV;LdQ*p2?a$%-G%+TV&S!DI5Jd97Y+75Xih)cRT^Ng6yu@c4#>{K;gtfd zj|AdrF+BQIN2?+G3>G>SUAHI_QcZ*AN-@0Ex}Jx!17mm{G*SLgj+6Hq%rBUnysjIv z`AAdvR5xiRZiZ3CSVGU}j)jf64Cy6<0mZxXw3mTz+5_=DVt9tm=pii>Mi_;S^RaL! zX9nZxkAfIpF-r2W9zE_xN-jgvbWOPF5mM1(4m>3kSl?5sN@WUbq%`=dC#K9tCJ&fi znaM3P*s>I=>}uUhdPcBs_KeUK`22p1&`zcii;#Z8^HqbzW>@zIq|pM|ti|J6Zxqc_ z( z(^IT}IR>j9ln#(%Tu+fb1*L{xBKB@e~is-&GFAuCLI2U7Ou7r;S@Fk zgyVskP-lQ7;iNKu1U7k_El?Vx&R(Y`P3-=)$2E>x6t#hk6Y-sltbtN(_&Y~x1Ak2n z2#2W;OVO4dxkaqCN6x_CT93R7m18~fk%zJ2Y(=%NUD;{sjVS*ts zZyf1L9wf~nq)#l&x+}#Bec;`}QjEP1m1^yJ{~RnmAPi?htLVq8N)2}*1KJ)@Mn@)N zhkJ1d%O%$N#tfB)2~RL@%dxq84Wil1>+s`H#Lk49!=xxshe@O1`{THRs~!)Ghn>SP zIKW`yK7){fbA>V+%{M℞QD+1Bse0)(gGo*tZ{V(smPX-zc=%W;TYB9n&W~fQH@r3mD;&kT z+tg7M+e|2g(nT27JD(^Hm^&87LbDhTXgUrFW+1@~bfCfS(YWILgNbq8{(Hl~6vpwE z@&{xAAAJ&7Q}0^i$72FwUJGR;0!Qdw$4f2fu{JiqFC8zn6!uV8rAFfkxs#?L{@z{g z_F*R~MBg>;Gy&HHgg3akFImdjYZ1pMNe%4pc?X1zPtRKd@`^$Io)(bzXh2$H1AfSZq@_xBsc_r-JX|1%Yxc~^^6ooP5b z#F-3YVaGHqh~y~gRfAB++8;r&*_`idMsXdT?<1TqZ3y|B73P#SDS~>^&Py_>{=JqA zTOXD3F>#nWX^$bl{CIBDsK=yvm>yWrj11ERJ~$l#gX4M1Etrmj{aK7se8W&~2E@<6 zfhMBNedwGS7<**R)Og)MQ#D2_HQ=`yQV9;~nFkLV#TzuicW0ttiluLKXFM)F4afcn zR98;NOD7KP65z!@1GD(q$Cz0rVBRe0QSA2^)58YSQySCE*(U73+0s7YD!1l{f&B)0 z%t32Vv|&v?l+8hFFd130U7RCj*o6eI+V7Yvbtb_HaPFi~Td)3a8l3U$8EcX8FKv-U zQ<0W=4W5v;keUe)et!VIKJ+9io0!03llLS}%^UL)@hyXALpb~-HeL1L$UGe5JLciE zzK2Ht_&lV~Lv84U>TQFBVIL(UG}!2;5H?hU9ru9MfcKx09wd(=wqJNQ418J&CDS$R zJ7(<0r+p2=O^POhP$Z>;G#`7GII1n~Fwn6vR<;FXqo&JkEG6qTlbbA%c9EC0lBj2} zWG|NtJ@5xM9n9p}&q(i)lNxH~LPWi*>Gz(Y-yZO--w6Y=|OA16kDmGT+KU6QO$xxo~BKg;Zn>ayx`(8RB8%SP&{w&naI^_TZ|Lr z#ZXp^T~ZOZB5FAjXvLkEo}A6$##M|1IC;Bzuk6MxYV z&sc51q34lx$Yr+9Wj*6UHPc591J|3{+h^8GS@v~FUhVD4^-_1d`UN#I;_;;+Y#qM9 zLPx;(myLk8Z$PCmu&e|BaRZLjj%dy*!GeQa8R;v7!Rtx9`}w*AbM+I*--tSYsOkLb zMx@aJ-)}_M{LGon-h>4|Y0NHLnbEP>cblZ?B&Y^!~1_V!+ySma#8zmcEA*CKYf& zR-nTPlfG!XL1rE;n;eMFW}~-TFGx=ZlCfM5DBXclv51Wd&%?PLQY$(tWIvZe@=j?c zSyY29{0euVpaRdn7rCFWVQF%Yec&EMuBn07LnzU{ zD8)T=w~kZl6LK>p%-$nK5oEw#fPQZeCh9XZQ1xA5rBW2WCg`n9!!oHY`P9ntZ9|#& zU9Xi%czMhFaCk4aeP>xDBop8i3vr^W&pur4wEyKT;N_Q40I6xQ_8mjOUo~7!UPjL3 zFRry{D*Kbi{mWM{0w{+D(0l33qziXEv~o$`lUgKo{tISeJ9F`?kd5h zpXubo?l*8T4_}Zxf>rOv8z`_1a-kJC;h>ai-|B6|LkDrcez(<#vj+REni2Sy8X=jA z@C9DhCKVpSrr{*FMLcJazDsp&NZ!`Wm~mKIOup7kZhiz!{)!uO-XM9K8KX^m&9&3S z7F*6EI3#GppfKnoSNcsacLj*&m#zaw3WUeIqc``?`bXwb+VQDt~)>)UZc0#tfT0apaImo?AH= zsOAo5GSqla`hXtrIMF5;9ft#3umO7 zLcwFdl(0rhh+t7@@bLj5)06`YIqT99Uy*K0v^C;!EBQcJs-?2#T< z;LbVhkR#yS`;zfy;g?3*Q3{VY3-J&deaDxC;E36DEG38`_5I=O_oWROOJti(vit$_ zKfp0|E(dn>2W%&}{ z?%AMZ%W;SRZjSLX4s~LKPo$pqt=>*t{fShJ$0RIH{K{}5rSNd#R?Ufxs@UlN(t&7;i|IM99a7B!rC2RG$REa+9{5b|oFO0MnuKWTA zY*@xTciZZ@js88Cuvm?OyI)8T+1sRerQfJ8r58!(6xIRjFJ50VJVz-!Jl7_Lr(eqy zOZqiqNIm_&_)6MHMk0cqF&gd%x$?5~1evV?XZis`;Mcg83@I%C$Oi76V5X|W2@v{? z)Si|y|19Tx^vr6O^6#0Yd@JSIPk8%h?6)|lKWFvNWy3#|!oxo&H2)m88gtCzpCebK zt>mU=_H}>A@2_HN1;e?YaL2_41>YI1pq1mE@1*4HaxZ0skERL8@=>nd+54!9PlUaK9bJ8O_(%hJPr9hkttF#h3Jog6!TrzgI5`-ZW@($gHJnEo zc{p!y8gH8hT1|b3A@$@6yM=Aj0?jE;m4n2~5`dIwpmpVd*kvNAx230uOY__z?m302 ziC0JJzRS*usY`w5;=X%{Gt_{u}+f;jZ)=-V}xb%!CF1;4YIkE86jow2vt1d{(sN z9vju-)UW}ZyC+Q`NxVS(=r8v?G=9Zwxgm*3XS0zNpUI0!6ODSUAmeULI$H#iJ~k*c zECdkQMe;T9PXxi;H1H=DurZ-CkNHh1XsSOMAg{KMO7}>r9grC)w54@yxKT<1VSEUBY`5ky6KDqy z1$-PL53qmaEu;HXIfs0q>8{E6!jSP191NAK`yw14pyZGn|3VmPNMyH-eTJ!s(}&X# z8K^WR_@*UWLG~fmY+B3MfH3mDW|~PiG|hK1n9SD_{+uY=h&{2kM>d>>?_{|>N#lA% zXnI^uB>LWcqHC-o?+|=ZriaVfq*?itur6F~KoV=SJc=~&G|jV0z+smslKX4(%Q!QK zsY*NJGRE9rI-?>Er-{JFy^lT~mAJwpl7y(D3cu8a@=2Rb)tQh+x-jS zyIA>AvXDEmg{j1^Pkdk6x%FI}ERZt)?npeu+_Bs24yT7Z7>2uJhh`Gyw2wGc>`{s7 z4oiqnlm|fdM0pH3TN_>-5D-@>HVD@z;_y1lK>?0<-`7dzYFeMF4NE(Rr-#=@61tk9 z-QRhFaf;FJ@04oPHX;QDY8QmE3$Twf2N3Ok%4qBTlo|yC?x;;GVO9N(N_x@i z=gydVrfe{|OKV66)sO=P`#tY;xKUSbO)6zrT7|k--05(yHr%c$&+tY0bS*iZMERrq zt(F|`i?UWSQl|T(EKZjD6O_#s=HgT2u)2P;&sQdtxCW%idjm=540bJPd6lt^6hJF{ z2RK(xcHeI6SsNLMr(atQXjI2%rdoV&!fG|KO&$4HyEDV9A>4jd?oK9hH|Pyv&-$ni zm*j+xGv)2L@HnA?oE>Q@Fu8&)gJ!_3EO{MSlEGKX?l)L0qROVj-E8crp2^_Ll^J#A zGW%9x!D=gXZy+ZKTbVYZsbDje(a_Dlc71uV{cJhxKe4j!ZLmMf*`KBC zo8duPruT&gCcQ%%$~*11y&2Q)1TVWUXe8ryjnZT5oj$*&zABT zK`5YJ%5FY!t~*`-cROK8Yxykh<@&Q~?u*Q-iGHnOAa2z-i&c1mMT53-PCKoWG~xb( zwxw<5JNVkDKW&$tW!kRxt1Sa@ZC83~JFC6iu)U_O3FlW^-(4@Ws*hqZRxr2mU6rGHD;1=(^WmZcJIy2^%hkn^_(=SZ;Tf4Un4)WV^;Peju{M zI}0?Hk_oCaerg~RAY(e0!@XWJ<97|lXI!lcDC094<2{3s@kxWR35tw;Pv}ghGbcv4 zIt;<31^X@U;9MOh_Yv+fW%McYdxkQ%GGX>`c_G2SY&6$=gd7%WswI}O_@DzZ)#1?* zaw>_;@;yO2Kblno6N3u&s;>A#`R@Rd!T6??*Na{*X6)0l{Pm&?#8WR>1G=w^zd71y z7ECz5`j*pzj~OHXK<@Xi?=P=0ee*5)Ht}c{7>MiJEz3`{km4+HMU0c<1TrQI<{Su! z6X{H-C}`5;p~EIlgd?_q>OIS89W*_h{@MEo6~3;9R}7~Wm%bMSe~p(Pjy1oxwg}mo zFM^+)1qlwNE?hevBV`%0t(jD6Y_4vm@9wDt7C4k-kS5~b?m2E=g*qM0GQ4@6PV`id zPG=@uohUc*>|%6H=vqJ)YX;rl9q^pjnV{V`)I6{I?1ZJoG=a5BnJ`(7CiZtVx0_l_ zw#alYi?6w9!(wvT-DJKC$EV60$|d~T58;hz@&fX17O&0GhXS<4x(L^aN95NC`3tSM zA3sQA$YQEihL5JppOcVmzOb2jn9<#wA>XpcWb>SKYmZy8Gv&^tMmE=8dn>APh)r+s zW8lfh7vTVcoOD32uW!YT$ANv?@DVv^4o{mr3s^JML~QiSWTdANK+$gdIgjk-dgv#J zs~dW}kj)P=`Ji0>3{oDpT41Jx#DzFfM+U5E-?NZTrtnY~9?U2A5jeL{o=Gm_xpREm zHYyswT1H=^!w*m8CT6)q`DHdgxWB&$*CBq@uuVycKa5R|2~uzoEf3T7{t8xu!eb^rvA?$J*P>ED%#guBb-tO|Z1 z0$%|S|0O2X^P?9jR6B=Lfn6))!T2iO(p5N_XAgOUd_xNtHd^L0O;4?q58FFw51U3CC$$%n^u~E(gyjG{Rc1q zt}H?K-b7J!r$TFYvJ8noz>*UAT|BxQHHtC;oiL2-DZM}?ornl5h zZ0QQ8>4PqHsb?I{$a+wFvKl2s!p6;VGto1nGob1gd7izyr!`k#*B1E!(i@M)n7m!j z@OF1-`-1Gm-DzZ-4PU;1EggP8Xos9GnLwTE@r>=TResz)&0EGtTXCc4ajT5_hKy;@ zdz(B~n8sv?rh>^#5@fuHG1g@acu`(&-{37n+Aen?FIZ(XFl20i)!XHn-h}-1TC$%L zW@sB@WZ*3#DVN$Wc&jS!LU(*+Rkfj^>IHaqmt2DH z$1#@=+Kn#%h`Zbb(q$aqEf2B_^*xgG3N+q>eL`@3OIULZ83KH`M{Yxe`n=QVT#7>e z;ohE&|4mJBFShllNc}NogDLmQxf|h9ncNn-mB~XauVc1EE6fAUI@BuKK*#2`Ld~&p z4u`MGus3h5nPqw%lLD|7)Pc==LO&;vMCe}CiUiydd#v*fPU`0QKS5EiUo*OqD*1s-K_oY<&0lBWV zOD%>`2jmR0!lIPkr7new2P)j9(zk_s)QXLXv^G1sPAGt$-yNogU20~fn3+Xoec1g z8hG3h6L`ZBc`3aj;3)RX1UK{PP<8cD4sfS?g}Muq+In|U?M?YrdI$MY99wiT6fxBX zZKI&$F?kDKkW7IP`xZ*C%T*D(8dRCCg12Nzz_ymbO5R3TXAYC{Ot1zxHPw`A?@x5a1ha6@QAFK=BsBX`6b32&Y^d8>&bGZaRimFefQ zm!8EWt<+E(Jf4%E$8|y^%9ffM;EaYmhn4eaKw3jyeOjKE%Y=>;+l;i+01v*e0qE5AoxFs4aVy z#AMFY|208PiNh1Lva9SPxsxEQ;|iyLg8PuBI^|#&zU$CF|&I!5+iJzacLJ5O^W8^rI?{m7A3puF$#n8u&nHEBO!!S7ludl}@vXo<1(2YCTbe&+my zOuGJvSiD)9wZZp$WB2_ipTbX5Beoey;xPFBC!|4U=D5dQ!?^1$N$xc{T)-VNCSlR_ z{}!kd*X16S$o+Wm%}<~PpJai`&+!*12GUmCG@v_BKmQ>&)OVyzxc`t?BX7wmgiQCZ z@5Eo3zK{6Tmw~vxQ#|z@en-xU&=Sjpy8)$lo!S$JiWBD6gCWAiVmY26(V?rLt zp_QwuzW9h6Tm^#SZct1>cY`7*f7#VWUeRX@kJTEn(Z9YOun9las_oUNjo?tI9Oa9W z9dAqXN6Fr|^C6QRZEMCU_5C5UOehXik_n1t%T&)c5BzT_mu6F1kbaH)HV=Cjvy|)8 z$lN@5rW^zDl)GQ^;QuYbfJswyY9pWP+LI_NuXSyc-s8D} zB`nJldWu%T)`< z@>>>@LErd~zX|z{SNxAuR@__XCg6YQ1zgRmD8~p%Z0xsAUJk58yMegI<~r%QNyb1t zSkaAntLC##(oM2Aswqi=&=f93Dca`wBe+e6rv=N~9@8{vNi-4TSBG-iMdpAY_4vkPs^Nai);wq{$$woFQ*_iyM{FO*Lp;WVfz^&LK?1#t`5R3K6Y!Fz!?;=|9oE-U1`BqniC16G`rRt{X<@p6t4aOS zkSe*JO;NfEL~6o2UNKDx!|7#sTP0mG!O&DXuJ`^LpvgBkTuaiFp9Q>Xa&~Q{86Ebs zouG5Im81ZBM^DZ8TA5<`E_i+un6q4NM0(*TMe$ujY!nO-s|1?sH1+t!T&628G0F<{h1nJ#hq6gs_Tqy`?szkemb!n=!B(G?~ zW|@Q~ZgdOV*M$50>!!-U0CJ2Ai>zS=xSLJB+~nHdQV9{rCmbr)GN8CuhDiWvtpET$O_!VRac=%D6Jd6V&8S0yk2FWx@eU1^3l z{b526tMe;VCx?y08IFi>M-bL*pe zXlOXB&sQEL3!3s4#k9yy0qC!((6=X6)ADX0)=(I2w#a_Cr}8BcN}%Kcr9Ii!l)g!q z2I0Mx`lO^O9NdKsX^D3xOz5qoS{Jkr!nWQ@4RV-gf=9z~0MtJJOT#g{k5Vndw1<|% z4J&c&KsJIeg|78g60NCu31S{p9OP@?srjYf)V#)1Gl`|9jizQ@&)n2ig2;Z#BJrnK6^;{8$WE{jBm1p48+C;i+=bJ7b2SsRNf@*w35t0*e|t)OGA{((0!1S zV(&>cv)+rjU=X&D4|2uyGZgKqQoOeIY{qYC>In%2N^70jv;yT68PBDN9St;>lmtO|4iD8~?bei@_-pJu=siMNMYd@a@r7t? z>t^iidw3?+u(k$w^a0yso>r(FAqO-9=SU??G=-P7Ij3S8 zHQVr=6FqrVh##%IMgHM1>3*Z+FAj!oV~`Sgx|^m7HSs2WG^<>v z#wb+;ycn_Uac#IK^){p-i1oGepusq$7481mS(QWrMdOrBIJ!V8c5&n`Qy*CO9e0=; zHs^id)8mzE1XsEZA@#jMZ%;!1;@wtm5WG4SjnsKun5xtYv=3?Sm1^PBl~iFACCkvy zAT%<#4}s~^m3H2ArEqS#(%RZ`&B8krF-!21@rNrA>^O zeFn@@FS=5gJWuIn9jD%E4(H}6o$%FQpF#Vbn>sbrR#8)NXZQ3|N^^7Mm}(B^XRg?% zmHP!>_B=UXX+WyA;O($>5XQ@(NW&o3i#NuKhP`+xU>}OnSfEs~2C+62EWnPmP7Cu0 zT;HxvYXKW)C=u{%Oqfg6P7}LDTeu}WlEOS%I6I$?~O^R4JEJPD^y#2TDeiPvVU=ft>iVAGWM*w zx}mOrij_eE>4le5;+0siWQ8fpr7M)7#D2m%%C%N0_}x^i6IvKiJ^|0IQsTV{OX1`y zrIj_!uR!(H_^S1HJ}v%6vv}9)3R{d7xMgNsx~I8JJBRZGbbU^F$6K>2P-_j2Au7S8 zJxWHbR)x(LX+B^}0uR@XtI3uGPH?A5CZOK-MXpoE6MI}suL`nygVI?@W^(lYs+Hk6 zysWPjTX`?KQs`EqWLrJg6c&{zwT0%Cmv?{F7_zrv!i8`AUpzN6PYw95`+EhA@K&2x~?Gt{LTI^QZ;@fIIjXuQV zeqnco<4#+`pF72|SE5aGEvB8rxdpFZRAPKtv}cc!EnN0*QKVs!wbR4au${Fb{KFky zxSktVkKQ`+r*9K~qb5c`<1!_-g54fA3P0w?WqLLWx{0pO%aqvy*}}sLi}#t@z&-nv zoU}^-2_UE>YxPSHnJhkgNI4&9ALMDVHc)xz znCC#n2|pggfy!u~$`^9wN4!;G<+UNoW5WhdEEqj*#K<8ySgG$>Av;k=JDh{y=eLwq zzI0vvwo=dP<3;f4+e#g>*r%EcxtfEHS6EG2YYK+O#d?e%bj4i199PZ@x`96{}`V~!KIHC?HcUvh6k$B$389y zH$iNz`HSqGKT#Bv_~0i>uF#Tk7V`~8&8Xbpg4*Pbst&NlnI18H4wm zHW^efamb+Mv`=?hj_KdPw_KDc{FpYX;^X5v*U{7Ee>~@JymAdxl;J)H_yd_evtAzE*3mQxfsJpeWKYHzi)RAJKGn3uW-wVEyc#w zaZ#RK&nRwT4_CuKl#dDN(T2AcEpMCD9(Y^18Hg(|s0v#~V9QVY;Q4=)`NC@YG}VFM zDLF%om!sPJ>|SnK3FGhK2HJKv?z#!r&cJP5A*i?P`@MY=DyTKA&F4{QCa7`3G2gy9 ztodf2pjLF&nar{>Wc0`pg_DO(_5PA!2dbvSxgQ!5^)T7beI&A{JU6#O{xG$&t5bj) z5+Hm}^~x4InQY_5&j+c$3-(*yCTqJ`Wn$Q+=gwL|G%i=0Sozl2Ubh|U4tzutuNr%-S*K}?RYkwzw^EookkoF= zuJ~1RyK)w(s5D|MxBNDMmZEA?tA?OG4rddN;8*?r|5T)33arWUdnquz1$MHe)+CSM zTUPXP(JA=XbgSV+uCI1AaCKQtB8xR-kw4@?S*=H2(2&pjLrzrGmgEf$`C9qN7^tVJ zZO8{2@*GF%SN=_GYq|1ooW@7HNLcfPuZx6Tlf%^k0=cWPy`vFopP0R6F~4U7#=LSn z?x=A5YjTtoS+_DeDqTaS_(OhFS#^*$8nUH7;90p zs;j-ohZ^!cN9u-7YG=7T)R&^yhTvaQ zSS?Us)+TAlcz;M{Z4(WN=cLN#IU-)oBl#M#8%OHa{`~LOx+W*6Lj*EGV=&e#YE*l3 zSo%N68F-MMLiMhb*e8W{^`F@&rff zhL37*sm{M?wOhNvvkCjjZtx72Z1jLsIB#83VPh>d6|eDp5C7=bcy=>&L)gVub~%z& zn?U|X5fQfRs-{w-l`nyjDe6!X+JPQPO9gttV65qa!M?n?-)bUo)l5|bMN(a(*c}}o z0$=n~gCk624{2mn3n*%!{(v7o!xt zvkt7k`?p?wA=f7jcIBuO?P(o6MrEfVyOG)eKhBLR7;okZZvwoo?;_VeDl*juUX@y!oQgccjRoQGAd)akwmYqrJ+{p5#mb!)Y! zFT%U6)f{})vwVqD+Neps2)DPvj$ZA^ccZj(W)@Y`+N!;M5iV=1;)S4`P(O@kChWiu z4x>D`dQ9|X+nFo4ZJfkAP&B2rxsXdOE29iXzyoX?%Ni z4$0F@G97eTMRmZz9@OoiHi+_l&;@VFcFpdf4i?DJj{Gpt8k6QM0qb{CKeJDya?O*a z(~!^^M*@#oJ-N;xo(Ky&tIf&8j(jF_r?VO+np{x=;koK}WEpOJ>usC4k=np@=T)Fz z7xfa^#Px$QU9F6?*AdIQs`JPz93yQp)Yyj#(ibE*r*A$skQh*KRob&TGN-FMGvU8t$MbDw;xcGNe7>LwxN1fbU7}QsTgjk zSkCuUbR}J9d#j3ow+?*OM{Opsq;qBWRjUj3QJxOg@_te$OAE5oi0vpi{-9cejOxVm zKBk{FT}z;TKXocuh(^-9_t``5=Dy>}FZEZ?*w=Wgkv&E&AkSOX*lVb<29`Xe=94vC zjYw08xe~h42BeT`i3$L)ZbTe|{vy#0G` z+h`X>Zdz?SYS{KYG#jj@kng!|qN#+t?3KalA|V8pPE*-MZK|c+aTN_wAHgf~I{R*T z-q!SU;Yvc=0DE$0uL|};p_*<@T)a`DP_2a@WYyYnI%Zbu_q3DmZDf@->Z~PW7H(@9U}UX&5pZd;39DGxyQ+lZGez!iCXl z2VZnFz3^Lyl&-DTO`7R6L2T$0lp0?!c4)lmrVt-`1dLTX;?ixodMq5PwiNnOo3i2W zu^xGaSBa^s1hSULthm*gQ21)RbyRywiyIqTD-+aZf_cLxYOF89b&nt+J^fZ5q4cPl>P=V* zogT#+Vwp(PfjN(=HSpbUWM-O2=wHXG4Xqzn`PZ@Rr*Sd7CygjoMh)-ujS zTi(*l^0mAL56;HnI=0BO)oc>f#j*|&(8ats5I#rUf!`-*z?gD?33JuHcyZ-pbJZ^R z;uJ!SY2js~Lgc`>1!@(N(}jOLCyxTPZ(A{x!8mqZ|8p$iXMoc$`#!`K0Fv=Lv|KhqJ+X(0U$*!g_>q4m>%p z!rcV!A}r2}kF4f#i;`y8OjPb8Qj0vsmDHmb(8aQ9bsu-UWqA%hc?!FW{oMaATW#E{ z2MYZk1B;(lX9#CF@MJka=8U5GYH!ip7(iLi_-fGU8C8YXd&bLft!I2CdY%EV!ZL^Q zYa^6bcqp%Eq5PWywNNq?-L7JxyrPG)<}(;d1tvUW^m-P4Wmq7@&~pELIxfU^Ka26v z=X_>9=8X8-pA*^_scD!InS&0Be0d4A;LUtDF>^J8xX^5f}eF+b*04QoT`2Ej(=aUP1cR6Q5%!AU9Z#V%Hl z2pdemwdDclsaaihEDdA(Y}9OH2QjoQ+>ew%Bp$8v60%hKh2 zJhb}9heoh=-1_mM-jKKg2eGrDGyc(6Ex$6n&xh74SE$$Q9rC;e#Vb~-8P+bp2b^7r z4(Z7qqJIxlzcj8}p0RT1-Q_<7b3o1JW8q8A_z2HDzDm`?FD>NpH5dHL&Q_$aQo|BV zU3@vqEvr|nOX0g!>Kw~T%K|jY{7TUy)JVF*7@Kz0|__AZn{?&>HpCK(Z;1Pouh&7)xxUO4RoPNhvQ8e>b_GkMrkmQO5?@ z4|)e6_(e6vIxBexTD*wcA}4%iQg~JEp(S(6)2_01UX;9H>8SS&Q@%5_wK-Yj3D;rln-m@X0!Dy`#*VX zDVp5Z&0N9sjrhOwVE#@#*5EaGJWEHDm2fmU`O)#imOIZwK_4YHGuegDgzOLmGo%?JivWSqb}hsr^Z2H}<+^H8lVmMD4E9o>hbO zmwakN!VxvXHEOqdMIg<)@kDrVYG4?t-HqRgbF5TtOY*gn#$_nFTQ|OxHJ<+H(v2@= zm6WM7Ng>jR_H5{}R}Ce@I7}Me+${~k^h}EPYq3KO4A%&*?8VLJxtiF+`*0#wyBn|V zSOZF2AMaCx1hNE!;A_=x?m`slz;6~YgLF0d)<1QMZ;e%buT$$l5GCi(sD|Kk_}ybyaDgyQHd-4RrQ2G zK4yH&y;5n@1;+k^ZsyniJ->*-KzvW)oCb8?)N|r>wV{6VjR~iDs@4H@tw8?l2A5t6 z&knmU#GNH8590oz*qx`x!Gjq0knSuA#Fq?I5D16VbM~a}9<8$W39@vgz?Z7)XtVg2 z4MLrQ&Ekbr(*!=LJ5Tv_hf!oa7b%%2gHR=(31w2NwhOZ$Du8tF4nj{U8^#<{L+k#B z0KIrjT|&r^?lk4f4bahKbQ&IcL|NtEdBs3HKm#fB8dIA+=60F4aKj>G+PLS>}%K6>28$_&!5VNm6KV}O{GJ*|-sRa8 zVe0%S3Vr_y#Gh1i%RQZ?p|E*lr?WPlR9_AtUumhm;H(<!N)pJ;hPJnC5=aO=2_*yqBy<9V4xu+uh@pyt zh*AWl7ZnBp6;MP`1Qb{m5Kt7cPy`eZX)34`!9r1l|1;(8y_?+xzrXk8^I@|0o@dUS zb7tmDy)!Q!x66hD$IC{H_n+fYe}s^-okS&#J@tRmg!VfX^(3j%rCH~NIdG0b6U0RZc?GX|ChGHIq*KxI#z&W81*1ce@^X-nH@l#` zpP#o4@4!jJCtZl@6%swBQ-Irh?$@X+@>nPC_N)^u>ZC&!k&G3Cxjm}xjjd7^LRv2! zr*`zch*{`4|A~#)^I2@9QV5^Bm!evd7X=^dXbYz}bjIbVtYCT^yBt-UY$zgPn=4Td z2aEXC6{NVkh=^T(i@HO`bmHzK!Xb-nk5*reDy5L)vPhr0_J1nUUhVg&6(Qtu(PgCB zKwd_EEwYSokjT6Xer1GR1@qyNSm%Xx4y<(Ezg&-cO({(m-iXThKlm7W=SEa}65pBE z%)+jI8~irc!b1mztA*Xe$T30*UEqB6(sL`ycZ!h%R%E>lewLkg`7PF!Xj`UD*juGNE@9gUV208;AV&uF6QTaFOU++J+qj2i$V0t%H^}i9QS|N9SNPz~} z39a-#awn=|2=3dlnaGoo{ud@GL{*70#lb}0P4qu7p<gj>-ZDkN;f|3PGCE_7`IJ zddGyR;R-gW+j{-qL^5bt2{jd8P1%g3T!mdU>9aEHyp=2Tge1S5=TPf}Bv#!f{_0oV z9AH`9rj}ICko}!`bJ%#=ZJ*mMvNQ+1c99+|rM4pHiZ08~Rtjg0%xPy?E_mr8$B43g zvOv|l7_R!No-u!U5;2P4!U6;iTGk)C38HWwG?t=02+iVg*;9>)lAL%I}E^@11; zqIunA)aY_$cKmxE|Hr;6(DIV#p}J};F~exT1QePC_Gt2Z&0_V42)Z{xEz^J>%&FzY zvm|ky8WR*kp#K+G>HX@wH>G4;uj1YZYpTPGE4b7W3He=zQ`j|N(iE9=VOzCE!P{`+ z>BxF&1FhhNYf>m^lhKkqJfT`8#8H zoeQA_+L34i*{j#mvAhAI1TOuG+=i4?~>8+NnJ`|#S?nqmD z)WRI0Onbg48HGARM|xue3enUY)i+>t0HqT=m7~5&E+P`Hm5KOhsi;bjyM}jHM>Sp{ zcO_|$O}fpBhqwW*U1v3%+(LHri>OQ|byjzga$UvnVq_OkTwUqz>5Ej%L{r~i)ygc98-DYu zW45cELQ~celeQk9Rv{mB6=%GqIwl>@o%a)-7 za*yA+!RlMlcMHmmwZ9>1b0v&sJ)qXKzBN8?YkjvXO}Jluf#9#m{rgb|Zi@;L;lSaP zlrCyz+H%40E%t!gNWo3MNW}U?{bxIoD)@#|osUg9i}KZ!NC%;EH!)x5 zcqJ2h{XunobjQGi9vlX3diW*utDR6sdU2S#95>nUgdBwSA|d+Qa8||P0{*81?i_ZI zrNlcjPi>=+N!{$}TkPL~`c(<0dffSHUq)jGP%4v{Fd4)uUgz@FgV8S*RBS)pGeT{v ztPzUI$;jU$Bdk&Ri!^7XIt&NobHyA4i*1Qf>SARF-91`Op$A3U!l6gJh8X z(jHaEz#d<86SL*L#;ETqKMNjB#)9yZ%${QPe1d#Ir;b%?kN7Xw#e~|i9Hlj|yA-s6 z_8T^(434|Dw)8kvA*FE2QxOxL(S0GPmRG#Ha}KEB<*ghfIuoJYMM*BC+4k;xL~R#R zsuDw)*@)*j2lyV1sFWmDNK#lw%ukd89kC@7Ro}7T4jeL^f2P@gqS~A&E$FHz)Rgk^ zPx&&)VQT3Z%0Hpb!sammGf4ODqNywSB!*dNLg%7Rr$4FAP)2b^^eWzyd;y9`u(?WT z&&lc{@tCktm43S{~v2&Wjn4_6Ca(X{;S~D z5N?R7PP#8|SJLg%)rn*;FFfK?kr>A}AF1njsj)0eXQ*DHd@CfMG82-6!f#^OJyU&9 zxhM#|XMymuRKLX`pZ$LlM%_INeu~gB^WgAW+SI!u0v$0M_LtBXXRBHGUY$W{)Esav z*F$*4R(3oI9Y05{$97yW=qU!RDWR9{8Z&;YGR)A3KfS{9HlbQ0R$aFc^fZK z6T@(v@YEO7LhoYla+BxWvpt;kz2M3d2Z{Q=Kmx_w5*x7R%!{kj+PdM?%ywY^caiD4 zOVo+V_97)7?1^L^>ir@m<{%;Q)&Pm$To6~MjV-YQTcpIny{z}irI-Q2foerrd2A~# z^BF&xa|#U6I7rC+eGgyF3(V|ba^M~9v`igGLVMCfPoplJUZ(boAw9XcH!KdI z<^Be&R@W3G{d@8uRphi0$a|5k(&6GFKlOBUKFb{ECodam>o?RY{>y!j(n)V%US&eh zpo5rkJ&PK|OzX)9F;)3)gi@o&jv6s~+ykRVr4&4pVLB5~%ggU6Mltxy`>|iF^X~(# zr03SDO)#+-_okZebpB6^_)8K5AMxhIa5(TmOg5eJvP`snh7tECX zbnqs%5xF8$k^Rcm+kAO?-g|13ny8TT!fcTal4X$|@1pyF0mPuaYD$xL&iSG`%<|uA zIW|ai+@hXSh)PTWT&OEUwM$9{KvwYp#@j)O$GjL8*6v5>0oz2sGAgp{nqP-gZ= zC8_d-T0u;~-J`NeL6U_ah4tb5Bq`8`qy4tqbbJ@(EOthT>7XNzLukiOz;csdx$+Y=Lkq%EU|+~(m!4Op z3zsXQ!T5XAK2@tK$`=I^ShE)i9QVmwg5KGy*8TsG%Dm6i0gCbmPlZg+Wt$I88Z{^+ zvYw6_%cf;yV>Z>_1cj7n(U^tPTc7{O#!TjYiC#e)Gdt1Xw@0voBg({+Mb`vJ&JE7> zs|l>9HU6u(I_y*rdBc?hY}JNCU#e6g4SR{nyk+~*x0EFM!G5(LX(K6Z4;1w60}rV8 zlOFh3!PA2|C93{-plE)3f3$R5>|YmR}ucI zknWLV5ph@;n=nK*c>B0IoXqJZdQ7P&)Dc#X$&uDfk>v%;*$gHEt_Nq5L#QIl*=uy_ zcmJ`RNlUyU5-qrBF@u^X1E;Mm8Q}4!*@ju^ope%NtKg(UJMnvXYnk{o6q2IW?;Pnp zAfS$}QJK@WyLJFk3i+6O#A)?xDEUzq!zn+C0?J7%e^mb=>VhEgLx>vCD;Lzd zWC=df{57O9ZSyl+4(@)uq*e{ZiA3G#%Rj5QSFyK9qVcb4zT&O_tNMhZRA8W*^y)?u zTA|zUGFB}t-rHAxtdnjkUQ)*^RT(^^L?Xz@P`?9ieBbA!31WfobN-!vuz32Bi z-L9x9I9!`+z&{EZ*4yvPmZ3rt`IS!CZ)z1~n$)*E&VDEg{5Au>AixJNM-~n4aTVZ= z0=)1yAK2OoKD4*rR`9_xUHR3HR5s{WJCm-dm0ibWUidb~oG(sKd=pw9UkE|-8cBKb zJlNiL_OU2zbIq`@8PBt0%~0@<_oj*#fM@5B4HRip{}*d|~x3YZ|Lk1#ZXm3i;1X z^%|Kgk+TXxcK%y^g}fp`D+S2XzD*y$&w+w!zxf}va`eZ6+W-2GnnphN*S@cyg1jhk4lkhB)*VX3~=h z#i~(nndoS5vKpPDkj#?a{#A;#Q;62jo3(|U4KdQ|*Qv`-R2)`rZYY27IjCO!Sl6l? z-C3iUhxF`6&(tVpRLSkCvmtVXHW%b-vbO1;>+Vc>Wvkm zt4+SnWZ#*$9$M$U!Gc%9@Zwb7b*MP(-@Fxg%JV1)1{6oof&FU3ezj!5%y0yw*t@Ch z*ApywrZR#>?A>KIf?rwih6lk$_O82zpbHDSng}{gX5kbTL4EAe9BLpw7pmqj=8Z3CO8G?5i zwF&#xhy{E5-Z%NayrX!D^EWwuQy}!KKr$m1(#Vc6Yn0GTXN(e92|iUM;>NpbLO#JoW(P77SF(0JpX3#?3=~2 zZWhnBnLNv8@$8z(vT8D-v3#1z^Jo^&pP4*wX7X&A#j^zLkP|a`R?OnrFpFowOm6;J z-1JBc7N5yYK9ie!7B}@wW@e-^4Fz^4H|tDp(wW?xlV|2V#R<%SGr93*al_5xMw`hE zHj5i;7Pr$ZZlhV;KC`%OW^%jCdSqA}t8Y7pMeuSwY#|EqM%W64xC_d1-e)Y>!~$NN zZ?RwFicLm15dC{mvR`ARy%sCkZeJO{!QSyQKA64ZWgOor$TB{M6?tC98${q2FXLBX zPf^Bevx44<74e!Z;6?l`Ru^~?pI!OB`zDJr-YXF=c^N;=Y5*_e?4roL>Zu6Ivw)ZO zTCB)VW5GxktYN_-77St4pd$--U6{vy@w&h+yAgGPT|||4kOkXWz-vXx$r<>`t3`cQ zeHO9c2^M_Hf_GR@vI&B}*smt+S2Y$)VL?6%wy{q)?R{zr2^CT7wW5LTTn8Si|EZENiUR&9ztayA@4T(#kNN9Z+(O}U|%c<55ab12*1F_ z!g)Wk;9%GL5pow1>T?lnx>C4^XSj=C!6u)FIL>}?4>5LacV zB-Zf}Hw6;w`iR>CiS>NMPXdYceZ&KS#55oAcp$NXkN86%G2KVJ96+pRTj)k0(Ptra z_d3T%S8$lNp3gu^cmU03AEj&n&1W9P6F~D>2cyk`>G_O0FRj-)9&MaSFt%Z`);P0L`|`r~sO6m&XEVwq2eIpxJhr7eKS^LIY^FT~-Cq zY`eS}K(p<#r64WMw#&`{nr)YT0W{k#hXZJ~UA_;X*><@QK(p;~Er4d*<(~kWZI@#7 zT2;Stoo3smOaRTcOT~h;2DV))1<-7})C{26c1a7M*>=eapxJh57eKS^(mjA?+hqW! zO&0EQSdC$uh8-JrVAzdeSMn;du4)tuTC<=D3x=~`APeTOU>Xb7v0xPozGT72EclxR z*I1ylX3NEbMl48W0lNV;uNw>4^`v=^lKWcTm&a~t%X^gt>;Ub&Pg%f@$jcZ!;;oj{tT`j}$mpt!EX81a*Tu-yVAH3}vP#k~VTU~v^;1VC*?%IOK z8arIs3LeLQ=$ebi(4DR`#b~wfDz)*}_{24#1h&t)RC=&}bP{cUz*U#t_{!CbX16Jp zM8}dl^b7S+|UuDhmIXI?vb%WYvK^7nhy^e zF*<+v$OoT)B<~s4`MXNn9dtFL$@R5T?0`s3YfP{1cNN3llWUPNwJer*`nxKY76YoJ zyg4i$q3R*df7sBP&NLn#J#+}}<{Dx1-*?F3f7_4$q1ie%o7AtOD%&XkJ>@jiTyWUs zp}XowW5)8JD;^t7kW4b&@wF?74nG9FYSO94T@C1&Un_;PUxNfT_J>Nb*h|E*b&deL ze6kWl*Z)u{3LEiw1g;>?TsZDpMlT$8Y05a-`KT+G_BrD6;2RbnhKw|5*4av)7?D2^^>uN^sO3C|w=Som2`#_nFS*~hS4)5Nui&g0rUrkA9B{xd9V+yXmsJv zLOfgTGdC)w(@|%@eTm@F;vAyC(6tyArOra_=R}$deO#Eea_OD3t{9wtgH(Ib{By1f zusT=$9aCglyW}b=-PJUSL zmRJE(*_?xU(bbL&lktWk-g#G+_qU6#c?#Wo(=|+amBBhJx#Eg;=~eP(vD%udBjELR z6F&L+H<38fN!m9>Spysv46?UctLCGZh;WW9pHYV(FMl zW(Atjta3VyjE;H0SP_eYWfw87Va+O{s69^?M#uDKT+fa&deDDEV_eE2mUMqIFqSHz z=BTnA0)>Xoao63Rn!mwvgYuq$$uM^~ng5yVY|Z$QhE{7v$9z=Dj0rTYokM8B5|KHq zAuHq8ko_ogD%>cTQ?&yueHN;)a_m0hUZLC+`H>QU`b*?TAmMkBA0HfbPa|dGc-4zZ z4Tv5Q$E!q4hd`2Kkom29DM{oEhLcJHPOC)3xXACZb{Q?(Ay5J+p#F%WwrRh+x1!YY zMjUi^RY+zW&v)#Ued3V2arA2BskrSXZxnML*>UvCL+*y8Jz!yG9ehJ{Evs@0X%i<3 z!;8PiSEX0qtgJ?DLqx|}E<5ObbX_>i>o4tJ7wLB*JFOOa>5u7{C92i}fPpaZ{h zmns#XBZ}s9ZnOkS5@ND3U)~`hMx(vF?j*V}AtqnGh(628_FQHGgVo}}d7OC#q@gY_ zlDrQk#-uCc-8iaDF*DGN?LHh^CA>rGBO-;3JcUGD-h6GlyGq2%aaQTdn@mR~#b{)` z1iZolI4FF;zwr%`G$RH}`dW3gAtGryqiReFIpLQw)vLvnB;OX1>eOmrd<1d?*9mrG zsxk9DQ=)nd{+Gr7a`;~!|102sMQ@4f?me^1m*eOC-*=z&jgV0I7DWPO>E*5Nid5a| z&Lh|3=%&3!W4aw{l;M+Ey1W7U!-wkxZJAKys?3ckUUxg|-H|v}k`uAqv&r<^a??9Xa84jExJ~GK|6WD zbYYo@4vfIvT$hh&+)^_kA{1}thCMuP?9f3Y=$Pz;@^thsv2}S$Bs-qfjWU9(SjNVyC=v$*s|=qoOnD zTjeU1q}va>d0kl1%#yYy@u~yeyILkoq24~6Q(?&O4G4#&&?iNJH z8MZC7c67lhcMD~{NHp`a#MFp%hqI(puDjjJ92)f_`W3@YyBmfoD+DyQ3q}+F{NRpJ z=6FG^8v+m0@`Ae+*23praHrx(Os+=q{`iV;D!Y5>jmg{bbkKD)vdo{5?eTp7B|ONc zpWU&ZARZ)pysF4@wa$C>XLnQxE>Hr~e55$?lG{*d?TTi2*j%OB^LcG)=Nfw1(BsI0 zCD+_Bbl+w7G37Td0?B)k?!4k|72x`A#nbY?xtlBh_({s$-;H?T{x-BoXc*k{h3#Vg zFoEvMiAbO$uewWwG7XTnoBS3}cRv~HM)I4kx`&hF@pRP|S6R9-J0XU)yyng!bD(;< zUXFghCf4Qs@S6M25K^rY&FY}{q~X_@L22xDcPy4Tk<~{?vr4?Tfk~+QZ@3dk(@Mh2 zue;%%8A>|Icyn$eUQ@dAw);!cU%va~Uv~_H^H#0q9rvqbtfW-C3-lN-(;i`3GWnV zGsp=D#FBlbls1k%@MK4aLm*+S&fagswb2R=tyon?!ziG-rs94iZ5*aD$HZy5^i~-_ zOIN1Xes;%rA1bZYlhAyO^5Z-(Y40ciN>pZcOY^Rc(q2<=&!5d}Vzf3G0|w5ko(s_W zlGgy2HbFvjX>wWEp^jk4Q5M5fWwkpBzNxSnM$=LiwARW{!Ejv#FzhcG9;u)mmC#%| zL<2+Y*u*xTIOD=!JY5xLrEndr4-V_3@t0V-nOA<38%0actFyHs| zP-Sg6rZ5^MX!E15R<@d(%lL(+8&iL|T8=x;n)L`ycLkx-R}-~07|3m`rR5SWfhx_k zEK)v!ez?VB(&R^@qiESAt(8(w08)bis#MhymG%PA)&`7u!<80MHo=lKI)P5D;YtgS z^1ZoCM_1FTDdlKZSbRnLdsb{kk>K~$v@|k4LDZR{)wS|8x4M=>o=gxG=UjCd3gk2O zwDQV$s-|eo$T*qo7^mQ$)X-*PJ37~Fc`!i5TG|ri3vF|M%&$UnL!iaSeg%L|u(AtoOiNb!L*W=adbUm#C1E@8S;mMMJ z%|u7Wudk1C-CIh~GZ^A{nl_z`k%*Bt;@&b2d@5F@&!lU0$s#Eut8rwhlyOEw$he4d z83Euj&X@e>STb&mR_X9YT6glElweB%#MNhD<2f1HJaRxHzO)hdmXX^rtBICMev>k; zY@#(G*QJbUO(ElNLPh|%jF%+;U!;t@plF#|SCn$4yOv5f&Wle}TuYjv%vuq z_o3*<#+8%lzs=FaJSdW0*(OfISo%;4ErHx$MKrVJTWSMC@r4?fKdPgVNDsC}`L@W# zvbFgk@Pan^QU@63eyZeXe<{@QzGFv3dmgu|H__YCjqG7j716TZ>8MSFJG5D(b_VrL z3FQwKbV_G!y7Gww+OG?sA4%wk>;X{QiB|23H;|Q2LGGl0qLp5MBiVfKv(-XJ)4kNamik|*3LcArpC}!gVD%dZRDy)cO@hiqefz=-ZyQnG%7e5? z3a-Nivo6Zt0zLXc?E$=cbcoi@qD11ub8RY~=>1w7>m}wh#LF#1wFcJ9I{an$?;>Mq z=zaImxb+dWii-iJOsJI=^V*e>uwA$jOMh{*?Zv9q3a;Bg6*l;agQ68sC zJ|uri#C@C|d*X8P%S$7WLlU{&dKorKYl)Z8OC~*`swe_5Z2_OV zO=#$BS?%1pz*w}V3p1lt@}p#NwyL9f${V9K!xdaM>YpGe?}V|a)TC@RI_5{Mvtle6 zr%eqni+xUL(Ya++Z$vzOdz=>L!z42ddb+b8(K385o6DCg9z_@4;?{$`jC63Di;3+m z5hnd|yjI$W8ZM)5oPdTFQLmjtgC1Q?7{#fPcgJIJoMeua^*J7I4qf}WR>$}9HTiPm zBn@W+O62?U<+djvvGwvx`SPnLwU+E9Pj;rA?EjD#zgA7;!_}_n2c=Hc z(lJuVnt=@Go*}%t(9J^ex|B9eyMbe$fa-#Fj)PH2`qHbju`-uHL#M+fNOEQ%Icf&V zq$J}I5tfuQcDbi*@&kcn{TY-28T+w7a^g%YZCPUDgDH?S3tjf*EOr;n+W3n=mRG0A z%e1mIdT)e5@BXTVS;(ygka%BeuGYvR?<+uNj5bZu%F#DxX;C!nBdxTBJXrvV_lfhh zG(nbfFSX_VA97bIPB$$;=RdTD$Tpm_V|V^1Ekq?V1wac1n7v55g3$puK!|Y=s4@H9 znofB_OQsnskh%3}&U0uxoERL*=!XffSHrH63%`n}CVibV&X59eA{}v1?+$!{dKY;! zq69s45axHre6&DJ5JxY8q)yDNK+F@=AvN=%sloIgzf?PiA)KxMy9GJDNoy}d4RK;V z4a78Aj+WDjIUa~z1#9fsF9ed8y#|NDnTx7}Yuf#k`N`2a+ehWigimzULG0f5=Bt zr51PGY`J_p@-VKJ$istgYrRPmNo(X!t^s7acaoVGF;}+ywclz=s zt+tOg+Mo97I~a9Z@t*RhZF*O$>7y-i&?39n^40#i<>{b}81a9*87-*A=nV%L0&Lr& zRj2cMM3-a$)~sPs(N8_D!k(?#@8k=q!eJ+eFX-I&wE8~Ud4Jl{_c6w^;@$G6z4d|C zNYaqx4(8^zXbtgk>yB+&Lq_1zeCCtpKV?;>lE!%DlDf5p15T;!aKQS9C%P~Xmk4uROVJK8oPw}7|IV+b-(rw2IXKS+ubMF@9}itapdnKbkhOk zi<7+2kNn<2cuyz!6+iL^hcG;HlDGPi-~Srk(@EavN8WiDEr>;CHX0jDfe(&o`!MLX z75KwuLM|rL{y(#f_&Xw;PWlGjAP16!r3i<_b-hRjeydgYqgV8&4?2btA>$_#y@BFS ze&{%=u*IH<`?D?Xy|a{efe)O}(n-%0(Mj$G_G}WhbBf4QjyU=q5F;hxp#li*uTGrQ zu83hJI^6UXV9zX;AN%-lWyA&+Gg^PkdB0;(v&mW6!zTeCrpo7@5|Zm zJDzvEuWG-~y@1BU!e`j;k=w~whT;O;v<3KI?Ehe@u>bw3!v2F&9d&BQub2USQX(D? zhWMyd!YslZlsbb9bENHAeS^A9rT{}*~>xj15RmT>Ry*%^~YE9aonA)`v zi4FvoXA=HG(`V7r{b?!JF&}Hu+WXTQ-9QTm8XrcM08NT??;PT#`=y&&4Klut$f0pE z`j|S799nVu?*QTeMyNw4VQ><6+Sb`_p>g z(Q5f<=lyB@@1m+$@oxFi77x{VG;WR6ATewBsWU*)w_pRET1xMNB|7|(onJ1mMt>!G zb&Fg-kbE&jPqWBv1Iaf-^_mvBZy@=fVtO5rkR?ESX!@#Kin4Y1QYR68Dvy-7DqOubsX`l)A6ca z+mGDJk31Gd(s&H--*0eDZ9N4dlFx^0cGq`(zn%}?mXipX^* z`HUa=U$@@GkNk%pS=EueGjK-~HNgs>t12>aktTVKJ zRlTZmj)7A{lJeG5zJH*;z0g4})pzV4C^cl%$RR^Vk9%ZLzHj>gHVDp(bEKI}3*eSr4J$hExW1{!LqJBHEj?qmI##W`TRo7pLY=$}Qyr=Qq5 zU8YlSd)!8eG`#ZPX_@`v0EKmFuEf)&)%8wv;~>2lJyt_+jZ1+CHPk!Mj&3uWPOhn! zA|=v1U#Ja;-Y%vzvN3RXmtI{g9^a1GmA!;r?T}zL#jMVB$y(!k&@m_9q zm|R=$fz9H0kwbUY)52-(WZgxYrqMC4AP1V#MU!eLDlNzAOPn`B~|u;%u2gR#wnT(HjlGXou8#2h)0-PvM*C`Y`1z1LrHJM7r)qfPW_y9@a>| zA6rPda8G9-`M(5+{gxn<;32MPI^t0@r8xYbZ~p1q7|;msn8v!IkV^997ftXomY!*% z55%3RSxxobq@g7B$pk5lj?UzyLz(&((pi#DXMvQ%VzsB4&G4H?O{epl>G@=s1Z{2( z!cYNXzli~Y+yxz`T&8hP>oL^R0)z-oXh)~82WV-bYFnkq(^79v<~I-v?h9J#{mJ46 zV!^#tD?|Z>l^*sNJD)9j@vK3T#LZCdNq$U9Q7FIq#e4HSmxO6#;ih5u9%O0@^! zV<9pBy^C2Soqp6lvO3+~R&PYUM+$74bKez-Dlcc`rv_{@E~enJbrU;Dc4g}c48?c- zG-(HZCj`Hj@tf=lVgZ&A*&r?O5R>37k?Q;H^{16+n%Mz1Et4)*c5ijC=t*`C<6}mE za_NB_a7qM{?K4j6s6UVSVosRR3514{1%F6O7j@@wCw&;{mQGhKkIkjmJEJCcmaxA% zBMx9zUiflsU>A`J2<_-@_VAXil}2lHg@pUO@R08+WMaC=vbgSgE!4DJEThlXPJ%8=a1X!`I4Y&3n9_U)zDCa-}mwrcU+ zf2-3SzIG#M*sF!ze^2(-4YC4z&nv{a=*He~t>DX7ln?aQ-(?Rx`S1F0sjv2dw^F_q zR{NzNbUPr;!5_YqR!i%z@4?bGx9yezK%JK;{s5F^G>yg%EW%%p8mMnTMeq#L-AV{; zh(84Wc+fz-H}l6muuisnxOBzg>z}qfZU`MSSnq9lV*C9*FFf&Pf+YsT(&&?oj4--) zs2*j#_+uz^ltjMktnLG7xf?Nb4&_ei^aIePMnmC>YtUU|;fg0bhaJ?lD}?!~Q>@@=3k~Ow0pX035yvo4q)%P7i_l6ril+zV{Fk zStbaR^Fg4J#~JqUyiBCl2z|D)Nub7#1mSIo;tv*T*GTC&f%w^m5^%%V`+tA=M=rdyx|B5u|6=qP| z%g=lmel?oLO@l30j{~kuBVkMa5Yb53^6EH!9O^em?RW&JM2RvV#e+aO4T>+V7{fmq zwK1Tru@85pQl%n|eF-~y`iw`jhU3y1WX%LXI!kW+A%{QkuT*^Ih9F@j6F%5vPWd(~ZBCdq-hAdHi|lIJ;4PtMa9Vske~eKsG2ITFPmEMDan=+iKbz)@Wm z0<~JA_=AO7xlrGZ)2BJA+_ONvFH!sfC`)>ca>H2#W$UvT#C*fz$%0bxIlUEHV!V(A z<-O;??VAkY*1nirdPWt{fC01(<-24cS%h-YAh zWyrv;0#s)?K%E4L|1LpSZP2rZqL2XMaQ~rEZbvJRdaXtt?PXkL9&KNZJlfA*$UN%v3OMeiqhHZ0k-d#YUH%jA z{4=WGt8n@kg>;!~K>bEl%i^#Y96y!X9b|_fl4KVtNGm<9m`39;yIvqZ48SB8UKJC0t{{l<0_WN(%MAYmi z!YS~F)=fmosr;7yC^qxi&~EDi9VDUr!Ga!HuP0FB0aql&uT<;-vLg+68<8f+NW1XB z4x)J7E-KYG2)SOjGHWh-@e@-n&*yGyY}D%_-@$bxJ|yAHM}MO?rb(N?d==znqchMq z6|6he-qA;6uD}+@{T{e~#LUo@_IVfVa1yQ0M(=yU?i(p9e>f~{acDC-JXamiDO&)& zETG_#G7p_o3*2C<-j@`|7Yyv9hRa(43~egxn}Y-t901|apC!Wt^6AecBs*og!`{XIFLFEX~N=qf+GLvK$WYbr)J)jvdJPhW&!XxAN{0TY19{Ko!gi@pstEhfk#FQwQ|d z$ly%&@k|E{e~k{6+;r5>Mk$=}H+8NN>;3Q`8{Ul06uFx7wVq5SWQtt<;xLk66t=Oo z@p(f$u#Z@p9R_T+1E!3oXAYyk1T-I~^gn{A1MtvV@9h2L2aZ$T<&$r1iJ2m;FPY`rW!byhFK9=IH>7{!eTR@~k`hx}+JnXdl< zl%}At-O#0f#6t$o;AD+;-yijJq?d%<{0WpE62>0TLhrr=H;M1GH9F)xUbw{z-pKLv z%5z4t4RBr1Q^_PL_1Ft~26;+KUHoUT2E~>d4_xYHjPjV2y2UT3LutRD4y}?ho&E*n zm!wRYzv5xJ6n*}$`cm?qgiXE($`%Pbg9mI@7A2OB`cuD7Zf99za(pyZk*@d)v!P-1qrdcO zN(maL7-H&^jmMQxI`BFy$v?)6#@WGQIDYy%zMNb^Z(hf!9L#tPsD4BLf<18Sbi9f2 z@_@_&^P9)*ZQU>3#DFM;CDwrsyrt_UYBl52%Y|*>ZYszDTe$y^?}KdN#_xs0Tka3KJyM1qTX|$ zw%91Prs0?k&udn23%Arha0~a6wYs{vnb8{akI+S@|ktVl6!9le5kEmpAM$ z|0v^>O!Paanth4!ItoNqDa#nenhRrCs9hn(G{xfp=mh|LU9)sCV;?$HU?W$Lny}wu z`(ya&Bi4LKeY!r(Xyga%TnO;P;zpJa$QCy0*y$En2RbIojdTBW^0#i4RxN4t#-(Un zC_am_v81t(ZSXDy>r84ctb@PYI*&>Ak2ZG{f=S`V?`)T=&pIoEp&CXSIm!nPls6cv zTWRApT#Ck};X6c+v)|H0XM83)L=ToR8dyNSy)iiKRFu)&g7H0$`|VW!gMrv5ZQ0Sr z1MoMSqK&Vyxpj<*GQcO7PPz={hpxGd3ha+&G$S!BM6pm?ILxy%##pDIb7mU3q)`FD z!W2xq)-Pww!A>;}=u!Z{%gwy<#%v{@NuV$J8k>>EF|4%7S)Wbv>E#MWJAsqSNyBY! z_g0pF05#ZcbXQ(xN!6e~x{arm*BlyutU=?Kg~s^9G+rT7c)_XhYr3&f`BW(MaWFtU zjEE5}*Z4#*K!(S7QTdZ=OjjP&uukAp_?%DSKk0^8BU8Yn!q;qO_f~k|7;H|h7;j{d zDlJ7jJuTkoMrySb?R4!*=*WP=KFni(c?GE4Qsi)4OGgezS2i}1oR(t0Lc3sy`3XjE zGE^c42SaR5G!~IbEyYHS=|HgEBvDD|e@&uVlF@+C_y&T zn$k#?VBFl7B1{D7fa`JX6>S})$A%{klH^MC${6L%Q8ujSfx<*Ir zTjNM}AQc%~kY9B}r61Qb<|}h;y`OjJt*1fnxwJ}}(TqWSde5>MF})ql-mzxf5{^aS zrf98#ECSbRCRRAFG%(6xdb?P*#I~@$w28Gd_ zHD)dHNnuD94eNtlBR7O2c0C*hXz5Fj5e&;1wVx5&>+Jg=@MX{vZC}S z9y(yK;l?Q|3}O|v_Xfk?4@4T-Ms>;+9wt>uz8?bP`-JXBS=#%4V>EuB8D-?sN<)nx zqkt*Yd63PVp~k=DX@ALodjOI@RfOat^9&<;N}B@13#U!2GkWN$2ho99LpKdGQj4>5 zTJnlvUU!1of$~IFx1m}4jK<|uP^?o~;;cCrbO?qS$#irgHXubkZ$w5^bf74cfvgZh z20z_}Bc>n)`xF}t^H1g(?2sQuw5neBhm1&t9FeA7kZ&|0C#7i{jD~5C2-9{NVT|*k zu8lB~$dw?d6(fxbKGfNfMv`(L9Ww=e?}a^L8&fC0xucA(;Ek-xzgGc!d9<-1l$dQD z1*~d#WQd%c(%KeY$h1dcrV0|^JLzcFqudCLXcaFq-nfm8BV5#hUC@eDpJ23S7l`^~ zKR5yPs%cx{f&QLgtP*f6lRX9kyfi;4t?xwmv7sUwpC0b>I7~R0j(*%2h_ntpZv27H z1?PHZ5?ZtAjud7-0Y;N#3b|9z#pTFc$_bBgE!y!1!6}`7{iLxJ#mi>5-odWc6tG+4 zWXF;DWOZAbHO14OR-bCPEKU=q8e7mDS^9UyVu-D}_bG7Nk61nz%HMn;C1MX2pJLO| zZT>^Vo${2Y3C*5?R_dxmww=LDg?tP(N7Dm%xL3~Cf7o4awgQJcBkxp2S$FXq{9Dx`k4Xe_^;U!+Vpck3^b?I#T# zu@J2o+-+fkOj-m%S`-i@YY{Jjj8=pR*fC%9(jwyq8RMU3_H#&cWZ`LUd=6=~U}bCx!@?vUHBCo;SvmrT&RdUW`N+7oKR;GO&D>oy{Kf%re7>jSN7Z1#{aq zGW#sdF6}$uiz^c_h2+)^E4d0l5LsP}br+*^sL+}C~Z2CLq3VmWRd z=5Nriw>ihZ1#)j31kDa5YX6qeSHTrmoXlDG_JZ7#E7y+lhi>h}-13IEjVTJIM{HIz zHv&6Zu%eh)F6Q-aG-@ko*=&AI-vMTl8C7J%l9>CP@p)s+Ag+1Q+Ui8AT^%Ie6(5@dC-O$?kQe3hPQNNT{ zuC~p1N&uym!?tra=!3=5M%#^cd+vc5w3V z%}9Hv6QytMMp3%U6$#!yI~$tdqWeDr>b6Ar+~|~#cyaO}f=T4;W!3oDxIn7RJ(lE1 zSJa9t;IWvl=uW7g7v`}z0ADEpV7F!`KIhrMX>#hl%NIrhAuqzzteecoFl*Y29{-yM zP~t%0J^nuXjV1mtuLFh+$-531iy43q3Enpy>kd6Ap##njKOW56;pThLnmt??>* z;K`p+6H3v?zeRbuf;Vh6hGQ?b7lXFe$Bl1sU-qHz;KBH0YP%Cge{4tPFZlX%)stXd zv4db;<2&P30naDpItYHV89?&$9y@6iSClLV!-!MxKW!Wge>w$xmSkAwwDGZk=hEtD zV2LI)^9*`>7wM`qm?@TfRGG+@XQ+PGc${F;kW0ut=iMJHYOJ^Jk46~?@`m6?CrP zs7lDgm#?CRa7Zlu{HpO8jvQx7vV(rc#G5SwPCvZdf$ohrv#@hY*g~As$WK4K*g>3r z*sfu8?2;!E-N8>l#NN%6KaAv{CpRV~7n1{sALx`nP@K6ixm2qPN!@o*+V)^^=nOU> zZ2Z&MN8CALy7INZjP@iB-}|y70^41O>D^eQGBz^+FRdePz^3K#z!nsb-Y}jgO>;yw zsdNkI465EX+EezMr00kd{P8WLCEa?<7(jYR=*YhT?JA%L@S8#T3DM?1#tbq-qHg~K zR31YO^znN0wlRfFmw=!C1z@UR!+!fvkKDm@+ORvAkytLFQFj4dDxhQ7Z|tzWYsgj1 zlk5fN+wUTw7$NlHIp(kALur)NirJogB8}3TnAida3aiLth`EbBaMR2VF=OyaJvYEb z_B%$Tan%)54|m3yWo6;;z7}eRDdZx)(!j(Lyivq29yk55m>G|ak;TKzBys~J$G+V^ zavb}1apFE(D6GKGSS*>JKVm@MBlkb(IAJlpxM?uvT)+YKV^#J50dwiM#Z4Dv*ihT- zN}H50=aWhuMXui}VRj+aI*MHXr4&T3gaZW4vUGn*a}a(fmooE7Y)9cu7@Zg$Mc$@` zo6nGTlFh|%GlO)IY^FqjO*_G6U4%IlzoR0-rj2B?FVexLd}(tndDvo8+H6B6N;Y%L zfDN`$l`&^AfHf5-cb3oXD5m0$M46^Qm8B(AGm1fZo_wt$mC-Uu{$NQS8*RQ%*2^Tr zT#$UTOmevkNv;=?f8sJJLvd#1%7WQC$&5c(%}KGMjK|&QDz> zq!Z0b_qa-+(u)sP7F57|0{>uTcSSQ3B{41u(=zyAMQ2!k8tOE+Szqpuj>z0f_8fy+wP=`S9`8T!T!Pd>`r}1Vp9CHDbSoLPU4QGx-`i(D8)3?-tfaC7m>Hld37I=gcr3FUubCsB<~Bq9IjbrRJmsj9hDSx0wQ z1z@cNOswVrd{)g|sqAJPa%p@G5I&SB{$Q~gUBg_)cIqrI6fa-dwR{;# zC)YAR!g3dnv8*E)T={5{>6iR0kEXX@tC zj4Zr5!F0Zh?O&an!2=>r$WQFw;#_mu1#^4OdFLeWmUd=bB$?jDG1jX}oAkmcb}APq=v>*D6b$tS z^fpT=PYRH4q^I^a*>tfDkiECrz0Gr&c!XFohxl~qdiFx*P?Nq;X-yZp$%R&Ocwg8? z!ueP~w;!k|U=@vVg~H);*Qi%;m;7WkHO(g5>Wd>+YxpAE$O z(+(hiA%W!vncuJ*RapMMHW}3ok~eph z=}}0IpB(hmXtNY)SA+n9-}d|$gGj^B>SN8V>?rO@W(`{UVY3>x^utCn zpDT|;PLAqo?@@w2W<%AG!)R&zB%MJ(Vv%D*pxn z@o^ys)u4?xV>d&YZek{2=MyOOKhT3u!g>B6GHYdCLKE6=vgx{4X6>15Hd1OXnPN5; zH%=slzq24rj-znc;S@9YZ2Z8P$gV2g{!4aspK5+u42_pE(@ZWfD;!~`)wWv^OJ`Wj zpJ{gWpA=>i;3g?1Ves7H0Gz1%EL5Mb9`7b5T3Dk@o|5J@ zcVGayaxMxm$b5`(XbyTUc;MaIwR7%WCGO0H5UU(krgP`PJHJ%8fmb{W124aqf%)Y7 z}7*Z8>1M)3zx1gP!FDpGzLlnfJ}KV`ekS z8~L2Mn<#%d4YF)04Dx&728mq(gZvg~5axL(rVpdMe=IR$6;ir8javbaU{AJpXfKv% zSqjnN-2=+3^j&PqmCq(d=Qw8**_Z;i^ohdQm=av4ofnp1D2ZwrW%=DNI2rc2?ehR41p<^0u^D5VOIo> zkQJf$i)I5wd634fgwN+wJxgD*+xD$5!^Zf~1k{0;z~>;o5`1DMK#zA9^&@l@`pX<7 z8<@pGknDmUfX=Q)U7FBc3=x*S0xpkW8z0+&e&H3fu7a5>BqF`yhYmJJ*8sXzBC>sR>mxsa>~1sBY&_ss;`?5vD2u*QMgd$f`enjb>Mg!cUQ9IjQiJ_%^8$&T=EtO zCndu{>;Vkzp5K>vgHZ$~%0dadj^Rs)%TMiYvcc+%c)Vjbm^DK%O$n-R{1`AlR;h=W zA4^~`b}}}f8jI^8rpC@pN-X4J5IHS|J=CK%qcl|PA#_;1*_=p9`3|TPiPJOt6IzGc z_qXwE_jtE?&7L7jwnO@dwn0&J>G)h?9lC0p+1HvfY_Q$T#u_-+lpkP@NeNu{M+V@y zYIgBh`5op8*2}d`5wR1d7(nB8qWE-YykcmNon{-saGEmH!D|d1y$if%pfksAmfE_@ zT&t8^e4jjS&)e@K6ML_gICziW1Ku-e)&aAN_tYLt_+VUVr=0yM)L4t7NXEpqr*C}< z@~hrmpPJhgHn{Xvz_%1QfuriG;23jYy8%JvkKk@F5igXo?@gDdQzOixjd8XYksLr4vYBga6hDslV) zIE+)q&{@aOU6|3MfPa*;Fy9_CUyN>9&@o~QBpf3~Nh^+<{4@1^$IKRD7N*h^9EDl? zgc(VC_oQ((_5O6l33$0SJ;hwijuU1LYc8g)PiJJhJr|Syo%u5%V|t1yu#T6oNiye@ zS(iM9H@94^=@+NW=8Sx8Qfy@lhPlPjx~DuHe%h>H6r7%!&#nL;4IOX+9HmowmWlDd zxosgBJMJT!3;VIl=`zolMcqe6cE!@E;6*_(vod+tmmEK7diZcna2{~eUZOUp)XQc z7M}bGUN7>vnL?ZWWVVUyJm(C;mfZ$VU zJI|Z7tnAASmVMFQj0-0ApAx$07JTxuUwDz-@C!_YAsK&H`XWkVRId24yZJ>k1-FTU zfMx58W(P3GZ@Ejn{v{yea>W;K_{;a-&AnvenhqH~^fCsB_*jmmRp*M$*E{SA1`GJ| zl2g9@%|VH{%9^r1f->WpgYv;OjER)tg3|a82W9LZW}<@O66bd9Pv{hd*>AHEJ2bsG zZS$9DGQY(?Re$C$^K;y)#F6W+Gwr#DqUsIvP3-^X?;pJh-YarNo#hWNKuNZ7anDWj zOSES|<&$?MAp38iEx^*hF^}<;V6*%mu>YKH{0D9F3rwCFmK0v^ZA=rxIq~Fb-Qi+z zCp?}xVHX{L2Q$y_awi`v-u!t7DVLzT?;;OgUR=hLfEh8hxF>c?ch7Z#4`o4UO_Rsr z^WIlOJTa2!Js#ruoZ!$~n|eEpQN4)TF;q#VgTg&sl!lUC8mAsdM1Y=3<03qr1X)Mj zT@c}E9WbMrLoY;lTH>>3Ft=w_NqZdp6%|{7F3gIKD}2RB+#!JrL`rxPOWIY)i1rvF z^|Ib4OM6NyLWUaj{W6|pc1#7=(qGQ9G$-2=WeeNs1vr{bQ63{e;-~28C{HSK++X6U zQsT(wMM)gW>O37ZxlFkdvX8lfI>e=&qCE$h=q?YNtYlf^ecR<}#4aj>k!#R$<)Ohl z4h^DoSQ<@Yghy(?fy~@D%6qy62>&VVTLF26IU7H7?~%gSuIQ;fu(h6kQ5lU`ih z2EBrws0d5*)MLC6ZclsGI&(Q^XfV-*BIG3NdhwcGB3<|+?%HbybejI@MK|f58W=MB z3w%oo{BoSrbc{;$A zfrGCH*r>NC>aSHU()Q>EMkOGH6|{WZR_6D#A|DL$_pSfG49|iPyeXpsU4un7Fwsa zrv;nLcG&q{smaaSMQXyzcqW4|J%TQlH2KWx#YwR~OZM!vQ< zM=<-2q-)TRns^#u{fLXfcXf1a>WLvKXpq@D^Ak-y4F!^EaKJi z1~SC z44&Xh8yIi}t=iUOuvEEG`3xc#uQxiOK_z2Y*1fWwE_VsbvpsbJ#QcPw&W1PG8z|<- zT+E8}jdq@Ub)7F|durJYoh2@}^Q88k@rp2&EKKclSYh%G%JDoNrd(p_)}ST3!yWu- zYeS#y4ntp(hUOq<=wG{gx&&xYf_CWP=|oEP_3QYD;e^+y*oxHCvq`HPn( z#al3_NbwqpmTltD!D9#Ik9u(U5VUc1eLW!bF$xYn+xQB4ZMtccCx*5f>{;j#@z24Y z^Z*O?rA>x-(nx=Q5qnD!Zwx6?L=@A3_j?k8y3hjBl=Z%Uzh_?v6NisIxW%;_t(c6>Dgu&0DN9kM+tLrIG#jP%qDQ0HYjWF$P;Dt~oel=>dg`7Y`K0nL*M1c2>c|H8#+oRdu3hhCR+zAM`aR-Z zUCAu}Xjh!&N1@+@f!_q1Cu=_kLdlMmxA<#UVZ4? zy7M-`p!V(pFrGQ@XtL1zYZ%<;h60owW<=#2O{y4MxCDB_5*#WxqD|;#gxE$)vusgD zh)wz{U%`aHT*xJG4Ggj!@4vUy`?ClvDeuE5z0?ZJPCZw6A7z8V0t$i4vpd!rPKOJe z>y6p(leOOMu=tHYxU#v2Jz3|4PcwEiUjOa39y*(Gr2Ha$Q5nWuqgn0zvdnyM!^q%O zUX1!EwZU7$F<;5(#)eLki$d>C6*9+ENYp!7Dg+|tw8?To*N9pFPGHdaDg!m-XZzmq zehl28D!zLcRDoQ2{kb-Jqr+h6YpG)NW~=nw&Aj344+?Q$D~yv*Flie|ek#B-u2>!K zMtu1!d_Ti@&ZG2pZ#;}VQntgeaKFLHl54^d<9{?IGO5G$MWo*W}4phU*ml?ymBMd(4@&9w7%M&1YZ`}J41k?H~ z=>u;HlOGk4#Jb(_Mz&Ck?b_k>8sFb7?Dytn%iBeVvr2x5LJ$>#;GJB+V?Op)gJF>c zG~5M9{RD<)uM?n|b|Cy7Y{gH#P2h<}i_%I1NUYV}xFv0Ul(#yZNQbWplP^A++IBt{ zfn1j;ekgh+FPKsjcZ5Yt>CzV}uT zmzfZYEr^gO2=T}rjQ&A4qoeMB+8dj@1AN;yHEjwk-Lq2( z5rtTz-{9KCq`F0NvOT8*AzWT4%h~<^oc87t#3QN3@UiO|=<7yzV=ddodD)j|yc+xH zj2FJ8lxkc<>T(uF1V(YZ|JAcz(IftbMb+5WSh^1n&OZj;398$_>W(*D;MX_r!F2SyyWU#x$fkup+D~3P7rV!{F>#W{^Mr4I@dDru-0kpYxePUU&$rmk3#kb$aAYg4Y|JeB##sDlT9L zHufKHe&?9L+;u$gk9SL+`nHX#^Zn%*F}xQWp1TOV-Tl~`14g+1$KE%@m|nQe=vf@} zRe-|Hs{Q{0ANY-e0y**O9C$ikIAf9^Cx{Jt z8E37w337g3f_`&GkjwEu&?EYZP!ecj%SHK$*d0pvCBN%oGXFvtjt~oEldp?I%^Evo zH&F1V`R?rU9C5l?5}p%ErUE{nO5q=qKxDo%)GntyUtDT}tqBJ(W`f}#0kFH_^5^1q z6Rdx30NY}M;U6ZL|D)Wn7$qJu;TCuRZodhKe*hewVU5Wn2ZxW%^2o;p@fT2tv2;;6 zpPc9z_1|XW^U0;fy8vZvslsYVM1)*7i|vDWoC@U|G@xJqQGLdw4(dKCb>zU2*0g9_ zgdE4KM)m(3A;%IvYNg19Sh+~Kh=Z9()+16*0T3WaNc$5q`T7VO@eaZY>J$|q-92$Wy5&#oS7UYUB%7fp@EMu9fvoZzc0%E1! z2Jf8;%0&W@c!Kt;f}s0=`-ByeM~WSKbN4YL@Rp!gn~vmpUOo+{{CQQ23d=*`w1rjE z!NO2ef3v3F3(E~nK;!tpp~6;8{zEbHyMj2=s;XkZQ**}2Ti^l_QpNdF-gpa-)s2_^ z;@cKlDQRaYhZ$b^CBBErm4Qdy<9>&z{yE`uw+wuKWb%1Kmc0RR)JQKS;BzuttjLRC z&D>(3C2m z!$ZY_u#`xx=|(@Fscko{LG0W`nAz}4rg0*2j72yd(cEPQIRfQN8R$f&AvNx0r^ zF>8a|Qx()_LWWfX$g7z_zF$q24M@HQeYcuiTYS`qm8}jqj}08UIP`ZPGF-~h7l%vc z2Ib(Pz55I*)i-tUfI$QLkbpR(1_VTq0Db6F!&td%$}U|hnPzvaDGw3#zP!IoVP3sR zWYqbf>D0cCd3HN8#V%_UJ6_KGKjvpPZEjXat|0d73o3$7xA*RA%o$Sq8Y6mm>9U?U z*({t8T3Ao6A}%xw=Z6&Hl>C8LO%~rXA>K701Q@6`m+8l%y7dj6@0udI%y;n%%}?vg zHO22tvR|7OpD#G59>wGaqoZB`?hi8=cjLyhr`Aqs@CsZHeki-ve} ziedeXhwTdYGaj}(*$mtq%VV;K^?U9)xHEWCjb>*W$+_9ZCbEZ}D<$V)|2C3g;kAie zSS(5CA~ARv&3KmdIiSd&B@J+kyu_x+KJZ!SRg)bZYI8O{MNSl30!6EL7gPEf8;Iqa zWf>p&_Gw0nOpZ6~Y6ec+2*mp;y0%!~UQt}f2# zXZXrAQn`K5MBjQ_=|7nxgD_KEs(ibL ztb%TFgmAHk9OF>%S4>Kk%ZMlK3O>e3nF`*Snx%qe9Nb2v4jPm?C>b{6S`QvNsA-CI zuuo>Uy2-I{@&*;YA9;iiY5~WUB+?A9T}amAL0O)W#8&i@BP8n^cJRrd=D^oiz2q2p zz3^HuIVCW#Yu{VG58s$c9c>JW;6qAv;X>oqK5`jYH-}v7y=F0H0O^p54G7HNPxS@A zSPpNVL9>k-VDvo(L1X;#dOx=g=(HccM<)w;n%m}cO-shc#MK+%+>X2pU6OIN_gFuf zvG)eZZ^E=3_%lC4w=xZkUT=Ug#oL`G*E4r9n0Fu)7*o80usSbC``ZkZH)ew!BS7xJ z+7Gh^SFaC~zsttIn=o1qPPK21mdAy`eM!i}A>;IyWCS zfJ4V;83AL_5%To!+kMFB!QHWICtdpD$)MJBIDW{_K@^=Je`+$rn%#u2_2iuhl77hR zZNQdJl-ok#-HEbJ80NbU4u%i2A(P}{upDb=_@K#fp~+b?Y;HS%%>&Hgc*9VVVe@iR zP_5IVRav|m&uW)c3yYCQgOJyAQyM{M`7S zsq$@p5qI0mFt&qCyiGW4y4+NZO*7``V`e}oD4b@VnB;#HOf&AO?w=vQB9=A5vb_o= zi6$8S0btgN{h_?rtdy;L6+(ZCiMaVSqXgHeH_kCK-kq-*unlyS>kxkA3&Q_wt?$7_so(EpF+yt=hLmmArBKU?Ff&`>H zGEZIytHY*V4!&uyjTR}hK<**@z%mwqmA*xaaOrm;0GvuQ)+pFQ`6KZ*FxWV*t#}`F z!lU@VivR*L;qiNo|Bvd(V32vkq;Ze`0W>T_by*BKz!BaAn73GlJ@Oc~YMDGJDsvs- z1*7iE*Ppw40@l%=hFha!Tv$1FHtaM~*Q zfY^LsU`eFUYG|Y#*~Zl{Na_r^r=uqSZ*8NsY4(3}YYf&v}l;xM0TH>~F?6iT-P9A(1@~~*30#cD2r{D?-2VTz@7>dHx4w~XU>ff`JZ8%AsgkVImOTI zw)uT|pt8@huuYW@Kq((P%(CJ~%Pa^Ia2e%8`HwIucmw9bK-RJ=oFAY1u^gQRm-tNI z)sN)~;vaS;RRH z%4tD>6Gwr<>vn(z$K<~_KvHfv@_+4s9370yg}&mouN`D~ah?Mi8lZ$d_-1dKaT3#ZE(SxbWu@}xmD2y0Py)Dm5 z1r`a66W&vxnrm{w=Z#2_XRxE|vMy-OKPyM^FHxpmkFt5MOWf>k!ZcM;jsCilbD{@l^#a5ke#264O%bNZwAM|^Eg|P~(ms$v! zk&R?O|0Y-Em*<1>gwm#$GV`bqh3!fU4=9ayc?s4-a4%hliJYle6DHtPzh9Ss6Bol8 z1phQr*_+RHs--vOy5f5_lX~X+Br}SGMV=D7!sbutSEY8O`GqK-Q~ir>_Ql|*uH*MIY#oWCGk9~Q!uWd3qs z`EaE%+PBDdc8J zrIi})4?7#g*ox9h75f!+&cArg5YYW#?Y3zJOU0-JmmbxUzL@{p7$s+f zSZ4@rx6=E=14gdNgvyHhJ$|_ysJPk?*G6ksv2iuJN$9AeiE%Z$+Yr1OUC8}vbZ54z zl%Z~nbJa^JJzKnli@v!qVuv9{6j9131H#}5BC8g&9eXUr04!~x z9@;_~QmbY_SWWXvS%n9BEHv7r%KYV&`tU6SrI+|2fb)jgtGt5aRva!LEw9`c51Az~ z6&3#c2^gd)o4|kX^=DL6!UXYx32?I#WS-*yJ;c33jPdlc%F1=|z6o%?3IP0JP^eiI z>H#Q_!aUW<=?6#57pf|Yv%|r??e&!ucK7EPiJh!%6ytO&dmSaa0CRpQ#+fd@%2ubY zqQV%jPhF)LoY{jSYdHWOjuq-D=I5Kr4GpXYOs%Kz-F#LLv>!jz7_i2(q*gG{D*K}1 zG8{BVt)1#C3C5_k%)3fXcIHK;be;y(zt}XmRSJhR6YDGd9AlIEN*}m&3@i;0TMRWu zq)81F`_?Ylgm3M#Wet=t15V#_ri_O& z_ogVd;L&f$fWu~=$4aboGw>DofMzr0ZTJr<3~de+_JNuB&hknA$DW~vm&LbG)pwgLZ+skX3*d!d=aR2FzOjZt@TJy{L2UL{N99NUs5?i%oymVXDfRh@ zVxEEfYD+sq#eGc9_H|ae8{i$-#4Z6cpTqq=M8GrB?{o!(fMFuKf#gd_skb|nE;5Ch z%KvzCn4$Eqx+^<{Z3MJlDwJ+ELGcd&Mfs0FNz{~~nZ;^c8%XY{JQT#Q0b?pWE4GO3 z`9?0r;s+?X#S=)mfuVwlzIPfJr$M7W!@dME^sh`~gq;|7Cwz!g$}DQAG6%k013-hsa%Op_VOIG&!<414po&D64Tt!wv1Pf=*u;pbUct5Rk~{6QN+6S+92zP~2>YG&3U_y4A4v;KTX(v`Ufp*S-f+`%Shq!q- z>9c0O;_leyI1jz>&MOKm7m(SA+3)==?z_SSr5xOi*?U#2XyZ)q=~F zt=VCavuCYhzTgtS23*!00<>PE{3ev+g*aI1xK^nSFGI7nN^v;l1G(kE>G9BGwUO2e zAIwjuty7W;iyPZ-56JvuUD#y zeF2CsLf3j5yuo0~Kk#j3kpN?9i{(!5xHTqo$o1|!%4bn2bd1GU22+d+BQw}+{s_cv zl`VTmfi>5SFx-M3gezkeKZ_4UmIRW-Gu?KY`|ScBG>@VIVsHq4H7~o6}#( zB|aLt=u_~?uIEXYh#v#O8Xg!mxc7^^3i0g7(0;MoPOD$!AOY#Cf2uqZgd%MF0qFiR zc4jF!a{2d8r8-=e8)XxG`EC%raB`F-?gQBu>`_WVj|zOf zz*g>4!r5PYl)5~m2nUr|=w93JRZ8VrnB81*WcTVtC5zpGD<~D4z)jR*@cG^wdzF*$ z>NU_96y5|XhfP1EUYDN-G6^>c&3Q`Pb z%MV(tK7;J^LkiqZhZ8?Qmh+8=wZC{?$y4wbh`PZ=oj|l~$P$l{`7RHY!q=F`x}R4H z+dngaRyi>$i|6lkl9yF~2rpN^b55DWT_s3JYz}A9 z_&2#+4b_wlz7%Sx!935tFu{=XG?S9+*J}()xG0f_e%MPPtTY0B!ufmup$p17L6}AA z33O&y4}j6mEM(o#lB|>gXLf0P-6-OM89w;pVGz);sn=igXXQpVaT8$iC5q|41-dq` z-~XGEJxu(>EGcjk28R&J`Mo%?gqJnFsWb~-fcx$yEU=v#&BqT-;a*d_TZ%4zHQLyq zTYgLVT@){vWPZI1Vd|?;Gm=wi749ih#k-@)DYSM2@|oj}TYwjG+l!t;dtwwjPNDrD z^IcA%-E9ruHLdZdQdvwMW1M3t!%qFF)DcULG0w3>?1D#Zy07exf^m0q&P3AMDAmm!n>SL z!}DDC{#HtftHv0Yq;C#PC?{-SQy)S+gFO6pDg4hr>Ir9HP|&5Opd8u%*(2z>#e*hK z`_TpJ zDLi{LZDrMsvMM2EsL!1dYHy*90npL{;LMZHz_KyM1xM=`)f4Ef zTs{MPYqYV_xIRkd2dQ>Psm*x6!%M?WSz@%>0#3H@Q!lWaIPkBRhOQ`C<{y+YY?3j&AN84TrTXRFM!URf}0LEzI+N5=6^T4lBN`;yu7x>`~# zSILeeLI%Y+V`2ZP2+iyagbE=K~j_d()llyC#i6MEiIMjb>hF;@uW*FNT&0=0~H|ok|&d^ zLb8VEm8u9yiHcJoEmj2*ohNNM%06Dajej-bcmC^WeMk=RMC4cG^T$Kdg}-K4mj5c+ z0uqfUFY~;%Jnx?lkc{QO2J@Ez(|GcPC;#vywHqYsd8r3}O-ake|DMCOa1b(Q=L+6Y zS&&wu7tc+FWFJrR@$)+#o($kgUq}Evbx6OFg9nW2zaVV{U&DKwpTk(olcT(kEW!2p zBcH;5&y#og?Bi{obmqhH4x_mIukfEQ^JFtmHu9u9NAALt*EnlUIhm>a*Cd{N$dmDq zH#)6CzUQ9f2O+o})6s_MXuou{T{_w=9c`A5_L_;dN=G}*OzScQG@gzInu*3qN5jlS zo6JOeq@yj;(GD}w2I;8(bkzM!)O$MWJRS8t6Lk&MfL_y4$1_pA>1lU>#hIwjnW)Q| zphu8@X4+jW;F_C>T1!WbrK7fHqNdVON$IGdbW~0{DkdG3G7}Y&K00jzv>UDr^kMr77y9#Ru1ECe+A{q5P=@-`R`8$b+L!pRF0cun){rOYQ{O*en`O z;Z0%{PiFH3TgZ?67q$?5l%fZ3c1?M*kSEi4a+)Xmc#@|RBoFzo=KNPxp3LCMFrFOb z$p<`%?F>mcPrCD@2~XB^er^i1J^u3to_xuZm@bgy;7JpnROHDJo^;~LcAmV&6KuD? zc7xa38lHAt&qKpJo}A^$L7s$jufx4w3=DWw z3xh?Aq1^v4M&Jg(dpv?H<_SiNV?1PFw3xv|Mh6}kn(+jK#kgRwSjB%~uxQ021_lcp zp<}S%V{QxTK>PtZWr_3@t2gsYvMMC?pyh>?kA}8tW(|8k*)PBpQ0%QAjkj&{0SERg+xOS9fg*L#IW(9 z4WfdjA~BD%)Y6ey$XRMBNmLxA6)i1^FE~prHHqb&rIwz=n$A*7QDP%!sii5gwX@Vx zmDtr;N_5rFSxR&@+*wL=HNja*boGj(v=Y(PTxTiK)e>hZ(bZaKDbdwtXDQK@-&sm@ zwZ~aXbam7y75^N^HdR*(Pq`Kg!T2IiBtF&^c~Y4ti9G4dlU6*L#FJ4xS<{@zo&R!+(CvlZ!n0fhQvGupaVX z8vj*^*LV|_HHfpbI-ptdwaJ0DQtIbHQe)%XX7^2qwy^1NOS>qt+tx% zktUD|gl^Gw*_89X-1!lDX13>^ODRw^hy^phSSB5fexV?(8u0OX_J`wH)1%SDJU&YC zRQn0*gE!-ImEe z`()2}cLH4-z@&UEAu!4!054=EHdN<$mb;_gX{h#slMTVT#YGd?@CC6A*~tn~#aPb9 z>IUtL}-PNE`(WW$HPqx!NE0T$HA29pQPlrIOEvdrh%-H7r_y{o7K_>FMc)o5DYoz$@*7Xz=Kk(8(9awvB*2xQNryxnT

G|B9 zaC|$p0et@xnf=(1(ZFrT8a68$%UW!V&gr@6j?3DE7sIy{xS(e!Zd*3!T6AHLI4RU9 zsMfq4L6)Zm+G9IfVkc06=8o3ls;?MpdLtUX)HTVtW*R?YdZ?8}&r1~d-mG|qt?Z}P z@=T-Im!`mHY$x_ra}i!_cqMwNtKw;n8TFc_@o3r%mh0bQaG9_$d+;V)FC6)6%=2(R zu4HeujEB*Bk~DAez*hO2lW?m%Iu{U_oohs&zP*PIP8~30LE7p`fzyS}`lxZmmh<_x z8DZfUM(=o2-IOEtW*=3{Oj#P2d8KuMj6Qy?j)pR?hc^|1M8t`vP)1I&h%o^BvxJhFbxv`l&TN4IH5L?4WoxTpFrY_jGfBcD92e z1Nn!k^*y5{mZb%{I3yeXU`4? z`S&Lq3*lQ$T_D%7qhO$M%mI5i1h!T^xF?@)v|8Nrvjg^`8|;*YYW78Ap)Eafz(2?m zK5|Nk35C4u(s+pRTTw6MI{$k>861`F^q@#7wZ7_V-2 z(Aj9v*+6ARi|=!Q?r{M{^_+Epo^}D<^eV{wy94x&3+SL}0GexRsF`!HmNP&-!0WSR zKDh<o^%1dG7B8` zx&!oAJ1DB>%*>RyMR`m ztCsXMcYrpvgQ9xMWq{0m9iYAJpeS?kc_8y72k7`9=(A-;I^*W6Ej({I=qxqpFo(<^ zIzYF(fWEo_WIpNug)g;mO$Ml<%n-kedoDXb;rqH26nP!B2&g`EfZh*+a+%4wgZGRM z&e}NreNu4aG(7b2%1e`s-BW$BS_F1aYcE#olHsLoxH|1ZQ~|gqx^1!Af`Eh$rpvI? ziCQgB^2@|81B(aQ6Q{#0&^V3N|6^m6SjsWVDnn860NV3Q)zh9@G}{^?H>BBo&{!g+ zjDsY_#ZC?PWmmAorRqvHdAXX$PMr_`Sgr8<;Y3awSBXX88%skg$7T07dka=gJbft> zt5X!XaLFNrKo6GD?DeI`0;`(>2Q>%oK zLw22LZ&BLFt`o+_E}j>-8=b#`i(EE?;xw+?2K6_=bDUO!YgjAaRWtPj-YCTM32a4m zt+qGC>CDdN(QBhR#B+sK5^Nsu#cp|%ZLWEl!r^?e_a^nO;Q52*TW<0X&E}24n^M`K ze2VL@v_-8QLJpPhM5C*nQ9;>k4+hLF{(`>^9syeu^;VSQ|m+jQB z33mCwruc%CE}Gv-Hk!iJt`J?C<@`|n(NmjdBd2+GsP#MzX|};>bqA+5+(SFmU3O}~ zX5N6I;W#;dTB*-C?JM#;oa( zsV^mqs&v9Q8O{HhI>R%MqE6fFQ`v#f)CQi#G@CP8BBi#YT8eAM;S?6}Eu2yQX(z;C z3c-+hCzUz0DrDXXV`JV31H053#7@+mjbqLoKUW`mKBu&;hIN2u8x5BIZ&UYFlY}a%)gX8w##z+)!v>Mii&GyjUD6*Q5bAdEe_a} zVWTbFQk!Vb`l)#6dFF+Syoc1L#y2;oA5UK|k$`>s5)MYJV;&YPii`M3fPq`V!7^}=-wYhN}qp&w6P-tf?P#?osf9$aOT3CEn zQjf_IUC|qUTTyshydgX|I3E9}$^Xm7W=U$-^hVy&=g4)=VlV)Sb zH}#^eA3|WzW zv9Ust{Uv@;^M=qvUb;JYQ7K&vY7%&v?ikhn|r{#x|TP^=|eVe=KW2))8lQ88iRR*+v;V(^B!do z17o|pYNF>un#}_vJAc=v4jbOTch#x!G{>b|SawgX9JL0bc5!~}xLDfIYyfoV6?XNW zTETOKR%iAT_$m7XaAlrDY7z8ZFAZ>6b}2lkx$j@f~Pgj$NsL~@=(!ixHw9U6@8OD z11YL8Jb%%F+m8Z8g!!6#Y&jTFoLIdn7Df~&Oe%%JINd9oZ;mH}W*c19cW^bE0`<@C zYwxk;AXiSTbc%&sIbob!eVN0z$g_i@8eBDSaJ8KRoy_TL?Xl&c=T8jx(Pfb>6a`sw zl6A6FG#9XRhN2oQHFU7_Jq0S4+tL*Ph$#nD8H|yoe=i9y(!FpBUHdQJ4guI zz~+Mgi!q`K`C8``U$z-T4xSKbJR(vskBLm7tdSm|yju@o;Ds1uqJu)vAgjE-DkXw_ zfGf7m8o2H+u^8FclQbS@C(!oAqKT|p^XNPb4{dFx99Z2!Q8r8Q6(NK+QaD`hKdJaW z@q9+J(fS{$zBZmOX*L)wrTC0WptTU`DYDf%=N1&IJ>6(fX|Pv^ZUa{6p8V*Sde1CJmZq+G+&$Jujh1ji%gMwwZ zl~S0Oz174QL+s{8gGyuAtvP$p#MhB1%4xTSO?{O-18MD+-3GGQ6kieI=luzsU0?Xh z&Vm%*Lvc!G>iYVhfVw6UGW;}6V94qoun;dqT`xH(Sn8VA%5?KYD{Q&Zc!n?|Tlfx( zZ)YaVWmPnz?^*{d#`xP^7{m(^W|f0NF#3*d<*P!(aKm;H!+Ig8nBUjh_j;IkJTp0d zZxoQ@h=U75j;gM`2;zmvagb0jy#t?Z`MN#y%>}RWQa+DpOmSJ#Yw>Z$3mV3&33W*W zvzYstkVcOQJd#nKKJplt<=AR~T5+L}a>sYLW39)78g#O0nerFFcF{6@Uutw`-x$`v zvv01LCq0vBAr22{I(IsWlEnS(@3o#vjf*BNH>U&1@_3<}>GAM31V_ud#hTuME%tm@ z-vqH-W-Lc74zQf$s68v^K)ev=C`~9>p`)08Qg`3QYz0$zDLMzm&C)q6<{A^y|G_zE z4FU5~?x=I{ZgXBAXSeA_gSvPg^Y`!!v^@i5In0X zw(?D^3g2(`mGQhovtg|+rFeo1QHqT2z#uaCr=^Lj1h!?cFNd8vj=Ay-vGw^YXg&8@ z6sgUI*a4PN06dDYbBHgm=s9f5=S#>BhWT1}PSR}7H(NE_Rw2dn?;h^EE!atMCgox- zvL2w6Ij62rHg+$yiftmh>CI`$@X@}{J%7?FxFwl)jE#949vbnrF}_ZMCwvx(MY!Oa zZ=A2DCm+q`%8*OC2u6|p2gmv9gwR8cxFKez z*~z|Ao{F>#887X^IHlnKakB5L5Tcy%MK9YFSc(!xmfZ;3Sf2K>tzp|tfQ^6UM3xi{ z-}ovx-Iq*4y)6RZd}{!X)eABB*@ zMt@|s4d-=A6dQdAz)T9jeTG4>3ir!z`22$BBU*@#lYK5Y`!1S|oW3>JR;vwf*IXDd z+j4NCf;TWu*eLOd%4ZpwQu3e8@Qn;%3R_I2tIi1i0i}%Y=LY4F-rw#`-wMHVmtv!d zl!d;go(D7=8%q_JswuMn>O$Y-5PE2*UCbuuElL^f6u;O8VB<7!@TxqkJj*9#;-m+Jn$5qXRaht_$UzFgfOY@QS+Rwtqwl-^pZ;Ie)PqERE6;}D`d%DqVG-O>Dq7>Qx z*D7D15PIl*ZisCtd2~KEsFoB8!*$QKzA}PmiY=e_x1X=`weq}5vytZ)U3jL*{`B>} zTp{$(`EI;z^R0=LGCE(=4K@HLr%N~ZMhTt`6cMzmvTE=8I(xRzY>W?g-?h=Bc>aiu zzNR6hP_YeMq+3TRqhj5lZ0zz41Ap)Le363Z1jUB4RRcWV(;Uue@kTDSQoP{Ui#=T} z{=!;pg`pQMHzp*Xnp(YH@PiZJRGn@I0W%=)&)82X}Zvv(X)zxDd4= zk9^ZvRn1G?g3?Q zIDzdtoDk1C?)A}Ag1^uU?Wy-;li7v6zHss3c>i1#&N=ZPdG`783F5-p){9<{%bp%f zD8W|j_sQaVvxL9g#YNo?Ec08%cx0bH)ybXN$SmIZFbMO_HQv6pR{;N6v zHG<;~pUCeOb>{?E^2{>4X&vXkDsZ;$@Lyf{uSm|;6#lC$S~>7!73V%3IZsEf;ejgP zb0%_|j+~|=m+8piOyn*dIZH>b(x)Ix>BtVe3I&{`BNyq&0X$QM74VwL+fb-3v?Qtv zum7UD@YVvVi{G_0)P<+LQC*k03Q=7+cSm(i!Lxp-FWdk>!%qer;0bCDw?j~KxR8#T z!=>5bTs62#fQrNU04fd#DyTS&3#d43a9nX|=)0r29*03PJ8VFX-sD+|owM=Dl6>YH zK4AlTlUFGYI10(56ek^pE)=8zA2Psz1;yX*M}BbPj?6f9fg*P;5!4Mn3js*qbQ+;hKlxln^4qIWGM*V3J=Az z6eKis6j};`_Z>nolY_6D`0^}VX&$}ox*)BK1CZznzGrRMRWi}lFh?QL)p$oC(bWt` zA<@+wN1^3T!eU1u(bgJAA<@=*jzXfXk3tK}2DO#Izhi1wLRq4rBaT8tL#xj?EnAl8 z=ez@t=;t>_A<@t8jzXfJ$BsgxAGmJ$tE}sC?p z_BZd{@fDa<-c{mrF8qdC8otZ2p8vvUR`~h(G<-INpXW`(w@|Y4(2tLr6y?A0iIPVA z7d|&KkpIHRL-=xT8ov8+kpIGmI*RZKXBxh{!3TM1_>=}8IHhUu_yvEA=gt{lDSqtX z^uFjetnNj)WHBHXHr5B;NGKL%o_*dv2jKB8{w9`GRjbb6i@n)d+&SMkX$vV@b@vJa0?FT$@ZP`}njEcDXP5stHfn_JLX@ zw)=@9v3YOm=7TnJxu_zN*N&wye24_zJ}JR&pA_@3?q5Ymz)Qr!FFxZfANXQA{H`Mw zoNGPBBh_{#0*{~+W6P!p`Pt^5eG$+_SVXGYi7fraS6J%hN(7!nDbDg-@x=-~2!2<@ zhkkC`72i6)IcjiZcIK-;2U(g0ceZ5tq$naPYbv z`}`HnCmnD_&2`P!T=gIWug= zRalQR(b?GD8@>TzwhZIV7x;=6fAd8I^h-B=gQeoGD3fpbUKA5d6rY7M?>9i*J(t~k zl2BV%#!lY$4UyWrQW$avD6}ytv@|JzhVW&kjJv)<(o3#*Kiu`z6UUf%BSY{WmPjZd zEpx@I{yVtaViRwng@+tZF*xS#h!)~61xbfp>6HA_S6@6}()lvOc#-N_kpxxx%@uy! zU%uwz6%+olS?`4mL(X;geQ{Fmd2U9zci-1o%sJ06O1621Q380+|LrRwm2|}$@wczN zSlq-*u<%e$;Fnt_*zEW#LQ*GJI-?(fob63IZA?0W<|^$=@JbV1@qYcs*HnDT#2XWW z$DbdPR=DDI{1@t5X5uZj@HpSXKRnJQv8flLBjNK*7=`$ILlTBBGXM*HGzFg=jQUV7HEf(^Hq6bf6z`?{S zrGp1bTu_Ok1KiV{_6d2lf5qzajl%&jF3YdQ6ZYXuB6f0BLhCoS*(pS zFo`AhjLVyB`-q04X5O_Uk=B*~oSV47F^^=oV;(6%&V%?w0XW{U&UnN`+wA8=b+MnR zwABmZinD#uS~GFJ&3@jXZpdNGxgipm4p`33g5)%%Wy9H_1cELIM=@nKxPTTzP6Xj8 zP;&qkP-5nifI!9ke;3g9i{dAliSjZ(A&JKLD3lY!8Qn!ev=Bx<2qh2{>`EPo-Tc?T@o*5#=mu%@~6=1vpTb49fY(@amFG*no}|V*RobGn}5Hob<0-ZA&0?} zD};irC7I`%h__fQ-nVM7`FlAxe{W1`2zor>k$Sv&-qXugB-s4Ljf9J)4bS%rMYZyR zD8EUg7Lj8OKT?UV689!(!R*~g*mZXmL<@11m{0;iR~cU1<|=N;E&`aYf=xHR1T@_S znF(Q?;;a|SLstG`9l*5wrM5*N;4gT}D&qyMM1dZ>5FLe}KEqKg-nv?(|AV8D8iI~O zmAA*U zY>U66OT;%YwabU7JN&8gVKyo?rYobC-bk|gtubfs%+DmeQJNQOQIU6mC^+h>ty^T!jQ>{76S2K=| zr9LJEp;^^oLu;n2Dmw zm9%X(S}<;H#%5Kv$#juWMHYE^mMm`jGY($NEfBVjbrj-bC24^bI*{3~s%RagD3S}z zb|4m^2rH^;>ueN|#bwoOEQS+W$l_yrIng3-85M87GkO26@9*% zxv{o9c)uTg5u@7q;PGxdw=j<9XZvQKWh-lH=h&ILS{{i&Ftk{$dNzwuHDFU6T~BKv zO(CM7r~F<|8!x>|a=BZ}7hTLoP+<{!O6>D8%`sJ)78EAs`Jzk+FH)0rsh=rdd|Ao= zWqqxhAgv`VAY&yP0%IFV?)HW@7bXb)_(qy&CxIF{)7Vz?DoTt;0$xs<*;`im9EOK4 ziZ#)S3(`?5-v|Yhn`*wUI&g&bG55JWmKBd)3<8%83eT&_ch+B%okR z`l4cN4tBY{R!6E&YCvW8EFD&i-P#wMhrQZCD=(#xa%@S&XO zHhA94`lCB(g#;;$uz)PK@2qu^hLc>>wWo`X7{z*_i+0yW1|9dBizNLBRdif8pxzdc z+2Q)SX@5xbt!&=P#z;#@2C{g!yNyMPkgtb!(nbMUyzau{TtXFDbOUm*=>Ihp`YGvC zf{eN>(Mua5?IF3GQSS|xdMRo|Z|$m$7H~^@XFnl`e!H!YO>)AX&2NkJwSiHGK)-F# zS8FI;A;eLJ{e87G=_biVN4@1D13@(%mF8sbsNVjW@`b~}*ZOOBq+E-vm@sXCHbROZ z8EF5eX*MzxVPKl}m5l=0|Bj0cIS5tIZBr7h!mJ`Q{?{I)y&yv>_6U~0;}A`<)8YKFT|;dcr3pned;Bn4IpL3*-RmZ1sO|lq57QnAQWsJMPBVUY zQIQRoPcuf$HO^Rf9;qdhxEL}@OJd)Q)XGSsNEM(LW0_T$!&;8Ajnal&U>m?W1?gog zgW)9N%xIhR1i@I;Ej|Xugl`fotG3N-;}~0Q83YUm9qL%Eogi%>+1M7=kJGA2TS%^9 z*_Ujb5G;Skm$X`TI%wH5Gi(^^2*t<=Hm6%{6`4-AdV;o5kWN_nhSQCkq*al=C%MR) zG}%@W!Sa`wtSz?FLDq^)wP7416w&D>LOE#^HvX^+KQdLzCrA$n9;zwUjFj3pT3ppnyVWL7g^|P<*S)Vfw#4A32k~P6Irc3S(m&lDW+Nk0_wzl6Lp>z zE*4nHOL3w`aG$aKWHGngqWvG1pGXbCzZml!8Ru*XYnU1$*k zhRZ5-mTAeNRFY(4fI9w`E#gx&9^3rl3N1>Is)V8qUYRKxjuF3GsZEob5v}_p8 z<}TDj+C-`k_HjZoOWa`do_7csde4{*TEnpTPpoX-jzSmZ&TZ7HiC->eF`Kla(tZop zT7}!wF}Aw6XEA?Vvx#_OF}|f)3s>86rHvdqq}1S{z56W4V#O_m+X2HFVTFx+Pg^X} z46gkIgbj&dL@pzSnXjBq+M>O{&TrOIn7k6c8E}i0TA5G;)oT&JDAgVqz!y%3Y|(~F z|Jr4&%bLf;hm)Abp$&F#EH<7v-CaH^KN}jW=V0Tug29Th)$8RLuLWmk&|IoEb{@`e z)&2~V@-MNPKQ`bOKD3Q6>;&kE0vut?|4@5P6pJm%WQ5VGT!3Mn)bq>{2BKM-LIbIx z1gsH8)rscj3+egXNVv#CM;OgBlcHzmfD}zbnaFB{foLI8G_nYgPOq5%>Ze*-cA-CO zxm$~dGr6Fl;4uQ{=BLF^AB)_7=yaaJP)MhnFkx1_}9)t>YjV{H$mrHuI1+#dFWXnq#~t zR_?G?OnPW#v)X?{XE@_saD)(x5?t2hm{wV$88}n?^tg?M+k`6b2N^FX6WJS9x!GSA zI0^%Tn59B)Oc$;_tYyNKlPP$Ttq*LpWhgBaPTX0C3;X>qg}hQWfW0 zb^~%U|KKd_+5JLrQNJtB0rNLVF6#GP7v?EyyPvdF8!gmt#Ce;3FA=JoPp=zQ!Y4Mc zMKCgD=j?>2gJJ86yr79;o_x!K(E%fv%343vs!D~dY$JlbAD=Dg@_`^uaM_=iwW$tb z3cL9LT3PWBV)8SH&0$ZQ#uag)_TDd`=c*ypUU(KYJSB>|%LQ1=#?!RpEZCgtwSY|+^Irf0q#QXIir@v5c zFj`Hyqn(ykkb04u8Fyi2aXraJZi?KqwF`<>!hFO*L$JFdXo9pBafQe`{kM zB+SrJ;J=Z`@krC{BrKy9{cj|~|Is?zREnnB`HxL`-w~ytsp1}IZYn$-HSn>vOlnA2 zfK`s(Qgf1lM*8YsTRjxv*1sBj2*^U94w-6Yv(-;*8YUPl?^D=;qZx4Wi(2DFLWYaA zFhZvX(iRh`VXZ81T4~_~ovy8u2I-ts6x(rGPZ!14muE8Zz5He%#?7?z5{Pm3m+CHM z)1%2S>6K8NU|5^F7gl<6ePXWk!eezDlWYjMFl|n8aUr`^cD;ZgzMmP_zkeFwdTS^L zSxs~iEhI9(XAuZ!4>@=}r(Q!SaFmzgER5jVW?{}*uf^OUi}rt*ACVe@Gc3Yg$o%Nc z5m0cw+hLmmCB>jI7+b0K8NOn_Bm0xvOC5olpE}GO6S#2O7W!Lz#3*GtDa9!lyp+WS@Pz0 zp-S>)qV(NT2a{<7q@sp7jX$H8FF9T7uMe#auWdKsNM?~Z9dVK)Pg~Hw!NG(OTv|_V8o*S zJq7emf;62_M~{5^v#oZ5VXO_uzdSF*F83hOUOORO?u{2Sw<7D9kc zjnTa>6pzJ#mv0Io_QErWSvsCwhfO;aR`>Z=78qaLz#%2Amb-`7jU1JkZ&FD?GRa0WrpPw8cc8s2>)GL%F$>K!;|*PJEd6a|8x~A(;e_C_F{-{wq8W-$ zr#&vM9&SL#FPh+s^zZWN<3y>@3M-89X3pj$*f@{2%Ke)Y^a7$pa*PI3q__T37uUNB*Y{gGjU(Yc~U;hlQFD2u;Cg5%2S#7-zWI-6A$|RzPy#^_PLeXf$eyTJRr5C<#-^%(;ei?^*7>HjcbAvFLahKCa7=zxWv zuef_ZZ#+ADC9D8${*z&g8y%u;BiawEs$Ua4-&hQqVdB;5dJE~SmCY_yw>5Zz!J5_3 zi%B$NS`EFSbc-Nk5R9y;r;%wOL72n#OqOG8BrtZ5_yepPVkRm9#_qnXN-bOL4hhVO z4Evdgl~x!E#$>qbU%R$WuMgz0!2GZhR6%5$YU;W3Z{n8VoX|@H`|IkZ9G3=)v9Nm3 zN0zYYSlg9&X&_;xacKY^-OB3HKwaF%^b8$6YS4foeMTlHCYQ@5UzNcVyQaf!RA-s3C&4Hw8ah zDN1HNF2={W-9UavQydbdO;DkCj01fQ`9Pv5{Uk zc1{z*r~x-1rv?tT)jMzvDD7Zq8@0+7a;OF}Tr`lEfFEq9SM-t$R}I9q*Q-bx!3xp9 zvnn~!UN7~`N{V#Q%Sjdf@0A?vpz9Km#MpIkV@)EJpvv8VoGSmbqu!aTyk#f7lhm2e z;Myo_wT^i%DsOLrgNDs}R`6;@7(9jESo}h=Y_ofSbs|olw-St$7W*~cS^suqFf*>G!x1l^s_Nt}oV>x>}QuQ9v5rWRy zD{t9)feU*FEO5)#vm3JNVc8n8soAoH>&8&a4j0ntL*03Mf#uFw#6pAHGwSBUHzV#W z>TT1;mxLtOhS!Y{v6!`)b<9r4(d7tz^!d_bLLMiOH~ZL@I|-Jdp1CZluRc!5&9?Q^ z+a=E7@eq5t#V)#aL5}RFuMlDonRJoMvqr|HG=^PdiPcu{pL{#(f^H#^AL1NF+By@Lbw z3Q|9-IMj#My0F)afR7%e*Oq9;oFj&XfPH1pONw{C{!suoT+zJ6~ zMc!-`%%wU4VDwXNR5n^v*uCL;Q?l|v*tMGHiV-%iA#KGNa(^>IzZxceN2sE|Z*UQS z;wFvNzbyH)g#{9Y1gp1X+t+B>y!_c>V$z1eEC!y&Tw^axyS19N8K;+$?pPE<#_u;) z8xxl%Rk9qvi@RZTKTgljroN=-EU_G_A!A~UAn$U?aN&ir&uV`Y6C;rvw1AAjnGdSx z@b4%z^v@oz=N6=xHCD`6Jwfj+DI^2@qZ#Wq(Pj&ZFlnNG*G2(7caw`13K6R4xo$xD zEg*B3bM$2Ws36s`@{L{2!Be3>X+(07(I-=Fj1nw=+%)|oI~@#8C8ygkY7&YV0^YEf z6aI`Y>27rX@^WK0QK;A9l4QdfdV(MgB{iVOZgtUBC@y>aihf&~6pA{(cGgoT4DOp= zgLQ^^A*ih6Oq<+uNVy?5l#@Zl>sGlLl+Vu86Qp;nY~%h}r*s?H^`soheg@@PlFc#9UEFoYm%<`Iman7kx4B;28+99>|u!Hc9E9i`+#n^x;s<)&MYU#PEV zRNI9BaoVyQkh21f>9eFU1Q$JVg-Zn^2@ras8xW}==!pr-U8oUHFnV$G(EXhyy23u| z5u3!qOJ^&_N^H^c)SR7bKEnG#xiI!j3<3m7ZIaezfX0+~Pf#+6bC4E`N88eop!|1eKj%YjZ?`W%SLg z{yOlJe?rk_t+)C2-=rMq&^VFikY9q{A#^oi0if`wb<>oT=F4FtjU3m&?AY5~I$dGmuB-Cc94`5O6 zAjw5-?*7156~(&nf!@SM20NX%T`J#2sA4;C10o!ndQIK|q476@i+p~%1J(uakX+R3 z2A66HD$(n_df6(Ovn~Q)1Ti-%S4dUZ8r*;g^Vo-&?@+N2-=dC*v{>kM&1V z^!kv1@~(?S6dyL2=L!nD_o?2EoN;}BZlI^2uvpiO&-C-2B&!;;1DLxLmINwW*~Zu@ zewWSe1dUbSrN1H33~u*?y&pLpo3LOQ!1gLEoAtT=rO=*B;I_N{^-lpw+7RZz0)gFa z_kChSvpQQGDzywH5ZotDoex{xo112HTwr!1<06i^V~khQ%I(nyi^Am0N9qXE#4Mbr2oT?F{uFIMzk1eiDudRLvcC&U{*@oBdK4kM+g2pZ!g6SX4z-aaR z3t*HG?NT1_On&DhaGb<*+N#XpVbO7zzFo9(S<-RaS{OlKD~{_)P73VtahOy6{@+Nf z`3lDPlqMITjMzHobMS_a@Ere_g(Lw#F^`wvk;oY*^j`%r;_Xb1l17aWIBcG`t=L2w zV8~I@uWiRma);s=ZH^xtc&~FdJ^VWx*GZu`!ANo8JG~0<%i*);mmVT{{d>K#Aa=`)*W^P1UOR`@>&EN6 z)3&-hSU3S)VHEi7wEkX!vAhtY09InS_%ot_#m*>;v@HsF=-al8^Fs!EgrAUxf9DM9 zE(D&~+L)sBKdZklN{dO|I7F>;C+ju}L8hQMGlMBRq6)Iz=k-#AC&!VDUrHpDkhYO3 zVDw-dlM~lvu!&P;`n<|!0*8^{-Ua=Z;Q8FjHlvYr8KThvE8B=hb1vJW5kX^{FYE2& zNd}Le+(z`2hx)T#HfjwlV-`1#84iW=v@>tBem}#3*mI;Z5P`f6dHQX>TH4C}j06Ad z&M&&RxZCPzn}XqH2q%oO!@uZtB$|P76JbN*rbAmxuIPoc#S0sP!NX0;lh^bl$B_<+ zMP1j+NO>$&YvlybvgF!eED4vW{>&v|?{&RERx2v)f?^X+{ljnQErtKb+?U6F@J-{f9g|yYtMwcbOR|n?9L__)hb=cHjAF!K7d+vEa|}dnsMYm0(UxwOj@x(a`79YPeMh zS3q-O;&N1Fw(S^-Usx%(qYD zf#bfMc1me~K3laWoO`jk5nNei)IX>FRRC<^zrauz|F^(?^RH#%~aF`u2;J3 zx=+$6HeAA@!FE8FxLxJTk`s) zGhC(5a4^~O`t^XsFR%Gxj0lDmOAYQVSQ7|b2?M&=j5DP~`oR6E6}BFe zbub@s4dbv?I3u4^Ch@b%`^GYPJ!05X!zU_p-WZ`O@0gsaC^tDfwEFWh>2UX`n=Hoo z7ma$WN8XeZU~Dqfq68GS`tujyi*0GR=r9>Yy3r+t!~4U7#6>qyBR>(A>usqg>;7HHj4CYhD9E zU-|sxf-^vb7DN9yM5~(9=?6*gx=Vk=wTlWqHu~Ma#xhv8!e!1cLu{MvD=M}BswPKFcI z*Z-^h5z6PY#*IPXrV8JbvC3a6CXH3*ZbGB~E=w~@o4H1Z)=Q1ABKBaX=Ub-xYm&@LcJE(r=8Per5Rd zvU$=EOGn+3ry~Y%t|O%qZtQQ-dXN9C_cv;l zU$6E4vZJJE*~@t#h-8}`S5x|0K1cbyN@`b^1dR13=2-vbTa=fNmLx&(j|W-&g=4@l zT}wjz3nabnAn`Iy$3Dij-Jgf1b@b7Ej*;|OO>Ek`|5j!43e0v~akZ!S3M#6slO8F1I}cW?=)-)DbwzLA zs=Qh+9VaOM??D#-bft7uDObDN&Nl?@{GtIQKJhjqiOcyM)=qByoJR;1gY;zKaIW3$ znW9{>O7aPS9cci@@e2n`i8evq;+n!5?LOo-Rd{0<2T4bJj|UxvxjGpgO=$)l#kgEX zN0S9~6uwQRBm8ILt4(Xcskd>2^!*ly*(?W+3GZ#9Pk+}c{jBslYosIWr!U6NpR55UU+2Iu46Ix$9b5Vqm&-6PMSy|VH4NZC!@zH}w*HF8 zz!U4F%Sv6h=O{;E82Co?>68UX@MK9YSt}oKKq#7l=B)htSy(&HASWRInc0KR8A6ov?>3Qws-xDcIn>I z>+{)aP}W~}Nae~?9nhO@pL4LOr4vOTam^*-*8{mI zFU1Rb&C@VjaF10&dq4qW6VhTkKDiVC?vfvEqu+ro6Me}QG zX2EZ`L$%<)d4@EI)2OjTypv9%#$r8vcBfGn6Ec`0!Zmv5#b-(?t2><&=M&^4Nt?5PoXW^!ctklo7)xjZrSE7>Vn> zEsxZaN9&6hN(b5PzlghW=r-v`rF_4bR5|$Dmh_4_qE<;P8SmYB!MCNOT%|8@O=pth z(~G6H(%*2oOmZA0;2y5%&Zn}{frY@BzYuXui_GcU?Z+JZB3q_Ja?6}q;yTbsDY_lcBrf|q{@~xuoG*^*%dj? z=31yMy;@pW%4e`~_{r78C|qmmeke7Sp2cNgV5*f5ekdKNu1}bBHUc+3d z$6rhR$ydzG2=%}cTK?%2C47xktK9Zun2ql$?6=90n#!p2!?in9U3cTP(pue-I{&t? zbz04;t$plvsisKz!4D;i;0$M7kIl4S?ogh;9`-RkD9tMUCkF?F!ub(=q0#Z2u@jFH zPfj(D!Z{&3tRs<1ZAsDW+!5|c*iO&F_N!FGIshN^J8vpbhPi=Iw>THvEKPBhPWV|~ z9EEPNEWs8Iqi>Zi!k#==g1MEn5H9m1#n@sF_Yo7}qK{_gKT?(boj2Yt;aJj&e7@=u z-YTeJIrkB(LG+QihF5k-O|H_@xWY_-JL}E@F?TZeo(cCi@SYRyCb-J1yQFtZH*>`p z*y!B_U{ll#)b_4 z`BdMM8%;~C<_patBbYC%&STeaQAX^YJWYA&DQS)}Yx0!RN!M*b@0oll{8*Ph%8aL_ ziLTpe91c`YdD@yps7u3?hn|);a9Cmyg7Wvb&r^Q?*whmDqnGTwbjp+|E+mv8k5Bzb z`POsNq3%=eBuAeq%F?}4=hK`2JSWw;<636V^U?y!y!Ns3N$!*HRNkC6WwfhD`Tg_K zxXdc*<*-Zf^D?j!eSvwD=)&Rz7ggDSa& z@}Bq^eqN-;v>@olWr+gOLUvCeK|9o=?Ck?xjDz1_xox{dX6 z8|&dktasa3$F{LfUBo)Hjdf-l>&Q0NiHkC<2isWdx3QLA#9F6uZft4HUZ!n++7Zb}>pLxSD?0kTJJOHe~DuyH_$aQY@8)yJn$SgKw%-8cs8cd0Py6I;P{rrbceSbthY(UvjIX0lo z$Khid^H*;G{-fi`52%=a*eEmGA{%99h-9NoJKpLjGs6oTWj1MqX!slG=ezWC7X92y zKilc2lW3qNM-5EXEGClpg7O$$%w$rN5eAbnL>N)V%*PU)EWuCK6X}?@U?BPhV}Hqg z{+&w2%qi0FzilD?n!R0^e|xFTzn}568 z{B~ac?X%{$^Yd?CF~2=L|Mm^@TMkzrnBQ`^`m6aZhpT^^-*UL}-(?(y`5dlBnBQ`^ z8fSWYIESlg=C>TK=9u4dxLRU<%i*fZ{FcL2gZV9ot2O4g9IisU-w59Ik$3e#_zNM)O+^S9hATKPE_A!R0$k?Sb@Wp~KQa1gr=Lsc z=Y0CPoqn#TpBL%p3Hteze*Q>5!)b=|)6abRnNB|xX*arte$J(ze)?H?J^fxyKjaV> zeVTqgr=R!fr<|se68a(2esm`NwA0Ue`Z=F|&Y&OCMx)m#z3)iduuA^dJJLMY5M}1O z(mP{IwORkXyVcqM0{n0IsVjP+68xidVOg2>dMmP(wztQg`VQ11!pTQBK0WzGlEp~~#)DH8*#ZeMf{L7rQpf9wt^(?67EE8QPSv)v=q zmqmD~yzr4U_1GckZuB*PjneQ%-=`FfRP+l<5q_gZ_uz-n5*>k5I_pU#+V#Hlj*%BD z8$Omg-LvmeF89i7CU#9=6-WPs@>=-H&!{Y0cN}&P^JgoYP9Ry1ga%!4$Pum?%I;63 zc6S4VvKF_CNR!=YpEeV>nRqkLQ0C3T zcpvi*@a;4W)Fc0pCK8_B{0A^R`3s51@Wgw$!Cj>6_)?PG%e8WI{s~S+xrTpAg4{lmAlj`_{iuxYJa)!&sQ%_mRqxqczlCqBWxV zYpI+X(fKvtTx^1Kkr2+wzaBYFgL9V#=e>Wcwz$SAmlw(NlsA{kveMy}%UxrXmp$?k97l}0j~lOfic};=F#ssl z;yRMPWrc&vu^xGqYcVTan&;#Nlu_xPcb|fLQYNSjy-10A% z%4WB`ge!QOu;6Dtd5LRVuE{~=TYmXi*9FE}za=buO+Y@t(9orAB)N=7Y&gYyGQL* z-l_wijvb1oj8xtlCLh5eY#7V9^50U45!<_l%f-r(!{mwXBQyxdjX>LX4U?xL{JR0n zd^<2f_lbE3vs`P9g-@_74D=N%zuR6uQ#os->~o)`fdLYix=uHO*KL19lz_<|m5bt@E#Vr^pHiv=PXv!XbzcP8Pyk>$v9lB}i zRQ>hy)8P;$bWi~UmfWvw95`f&4r%3!<+GF*#sQ0S7`U~{>_g<~B(QEiSRUt^X)Hed zevW?^fxlloxm;HZnp6n#*r};-Pj5IGN~M$GS)q8xtiDiBFG6g0=4O|A59WlQ9V{Q{ zYG5^Rq*q57m983P#4MTST@qfX=bKZ?#|~Amp-`vwRKB*Z@GQQ@zTR+qDw*yntnIWz zP}@dhZE;qcyXJls@#r2yyu{b8eEL$kKI>nvVd=T?@@T@+ItWkKb|chl)IJnKne@)o zu^O#Br9t^}wLB^}NqUstudxHa*9hz}4wyPcGI{=|UzQ)Jf%{kk_xdDxI5nzgA{zAp zgTsm5_X>tinf*%nIKPU@A<8+EGvrAnIu;* zvEcc+E`*`eELLv+b@?G0w0Rt~y;J3bIcTRG0%)^UXk5z<`#GD5l_w9Cm#~S(jkXHL zAv8@M!4k{@c#G_T4T@Wpw-CoFoO2` zX@GXF30elwR6X)@SzhnDfh&1^P##yRD?6TgA0ut|b$PUP%Np8#ltUY|jm63-4^0@a zwd5HN-Vrkl@Q8TbPnw$axY|K?9x5A*ro-eZu1`65&mJZpT+lwEH1|g)c<<-oF*$@T z7Y+lIvr}CYl*?!7qLrsc7e^?r zqd|I0zm`Vi=Dp#fd2gX|`OyXQ-uwr3GGUDO`=g+*tjR$esjNR*9-EU?Zgp;IWk9&O z>3Ehw^3T<%Y^=-8PYTI)t%;{|KuNw6>Hhl|2;?nBXlVm9PPkuKJ7um0@5dax3yza# za*bs3#Sa-2PMTizV8IOUubXnH2I^4`RG>nhL`|DfA&+iN2ZPM~SL<_~`DzKT=@?ivQ zT{Up(R?b;2A3>~nT!qS-u0kl^Oq#k#gEF0m^3gJR9zmI~98e?%g&Vx7lu>B_b#M(T zZs39ZxJE_H?iv88GXkj*0ohdxV&BLCDIYpDyoGe0@T_!Ss54A*LRq!~0OLl0-3*}n z)dy7t1c+x0u~SDIn61&horA3`sh5XRFIUuK7-VQ0fatpwBX(d72;5D6eyW!Iyu$QD(M`HyTm?FUInJHk60JYIKhU)#V6a z)?&3&>zaVdgLWCGjPhOTl#%O3P6laoa10OZqmA;=+@$2L7feb=nrc|A*5Gc`5C?g| z5I2XBvZ{i|#^hCSX6xF7Len{m)C7?z>Qn3DD6v<$ycJ7NO_`sxV5F|dUBTe3Rg{C} z;eJhYEAuL#G=109;7c`>WR*MDfUtC6c_s7b8Zcc54O;`$-e-byw-L_EYcM#!*9!Nq zm51geP7%{k-LIQq{Dz0YiLnp+4jrMK5|Mo_m$LCB2<}to$RlT#Ozlg=(y2%yo;Nqu z7m22)Z%nBBN=F?dfE9n5s!u{w@)e9Oo!Xbe>Lc74;S5^!MG7giFpg|IQI#$~T&qc! zvC8(arXMmZ->Q@3$*$#jfXXu`aY}KKLTaq5ioxMVbtz7~MC5vD?W(nsthN z;1GRMMxX1osiq^>s;(2YR-Hnv$_?ysr-Jq_<{q zyF(uDKHw21LAcTRw+K>Lu5-(3`7;01L@XBS2{Bo{aRY!HssiDr*2(x5CPVjFt?OUy zQoGK0Ft@;Hbg$9cM53DGo~9Mh;#*BnkH^=X2K&J{m^q1Q+*>p-4@czDITg03-m9vx zX%nEN*1W_c1&ZwTf1i4gCMJKVL9FSPN75W}VmJDEl?l+5CO}a97b|1GoH|7V^r!~t z)tIUU{4)kXyG(!{$OB>v3Url8)tt~`Gr?yXFntpEDh^5Yi3!+;Dlk{BFw;#+AD6~x zjXLmAl@z*rfoJsYoL;~gfjCe&;LeTWP<%#)-y9s{WO9TChvpH2^VLScS!jYYUxnk& zV(uZUO|MD~?w(y_9z8}0^~s~h)9y$85VrM!f3)vWKZH~G!yNl&hr>Cn)>U4v0SX!Q+`6=a~ z3CMX`O;VdbQIpi>5f8Hu2+({j$(p}ff1uhn<3W>rtS?t{&(xPkxM%9ipY_5S!e;p+ zY8CY!JS^59ym;tTAE@aUX-QW3ZTbUM{*wMcunu^X!J-}>swQbzYt>}nf`N2)SUiym zw(Sk3z7i;mgysB&+5;{eh~vM|~jlys9P%JzuLyLeKc0Gbn(A zuPgKiD!Ng9pl)2DCaHb*Y03Hw6?k2Lq5|LO57edE4=}jYk7hNAenk7UB&$u)AE@wy z`U4eyLw_LL4kP;W)E5H{>FiMK5}vvt(iun`jawgt2_tgnzqWHxc|0AIqr0M%Awxf*g70ZJBmJ}zBix+rK8Qn#%Kw$ z8l$Dk`KQYZ#t)%~t{-UeR-!}kxGg#izqtHkg!1dt<-=wZ|Ko{Tfq%sR_(z+b_(waQ zCsR+{QFXVoT$yu*Ji3@JS)z^Ha%I&S^4PHiVjF|7jRDxk%5Q`CIOhzxe0(|TI}^0c z{&js&kNwl4WM7JH1(z##o*^GPQT-(Ai-p?4F;-PJ&>4vYh^LZ?j&wU|b^{o! zX;T4+?etDjhMXlwO4s9@t(vh~Ip-{ScG(k)^o%`=l*TpV=8izIS&Q||8AvI+7Y{jV z7_x&$>eqJyt=yz%AKIjxHFmb7?QD6*(6UqXPl}OJ&iZ)RXe#;VEqeA0W!KqQ={_0KGagr5=b$6QB6>zy zMETBflV(vXBDu^B5oJjwc1f;Yt+?$NVF@FwGCS4*QxN;a}mLabvl0}I&u`TPzMiQ1N z$SS+*olnMihqL+K8CK%VMQ+=PZqRKsInU7|CTqQ#RfGW`vqP%;&^ zY>T%t(dPuiTOE$aY0xmB8Ja{3N7S>vE0MNug|9jh55=gzLYnY5gi~8%;iNqf_c8!j zuR+MVYiHy0!j=?OF}krKk>b`+sxKW+Bu$8o&Q`Wx9ki#fRmn(#2uR$C)sc9A2vfc7 zczBz_$#xBwW>k7tWfU;SC$CTH&bgdnDYd%erU9cjKF z;l5}&_%%8TKhv8BqLZ)uo_tXKLy$y}7KL{?N59U?r~e?C_4Gvg+6SU86xGv31gk)_ zD53Ak+cSI}!RQlILYHb!vEr&!dxp|wU5U-T>9!a|MYv-i`W$;tN;*lf=y*I9)?g4` zX0a2Uu?mGu#2r|r-BituNyvbXUsL6}VC+NnyQunI%1Z$%Bpnb2v3JU<*}kLdPRaJ}EC> zC>^+HAH~x7Kag)U;G~o4(s2@DeOAR%H>C|Y>0$5p4<{KBPP`S7j)M8ph?31zvk4`S zsv_HTsM-!a2iu74>L1EC81Qp3RjlLZJFNdIelDf70Y8_s_xp#ReWaPIscI8~cB?cK zdT^+;uQW6I8u|6bg`#^0)urR)PS$4?CwH?(=%V}HJ<8-upyKYNT!ZZXIpyu2?1r9Z zE%)3jbFwotAXLl!Ya^jVm$g>wUh5#gq4_5)1zt;D;ALQ+5v>b~s`jJuKwTs>OOvWX zk?XF}n{QRWZ(Vvz+PVovD+e+CAka|1s^AG5!BCX3ox{8>U1?U45P-XZUk@0kjlGQA zv=v-VQF%-i3ZuKyotd4rb<0)?)mA+#mZ6Ty1Ga*60`jI?)$7w{`*BgR@;i;aZ! z_-6NQUD) zzZucePfaip(q5I{ier(^u2gtaD25FIWN8+Zf<+UpV{E41n{SlAZ$Qx{RHcrh%NPn& zqWUhS{hMIfAyaX5fF1`=Iij^dX;o~`%{`fLJQays;wZ2@kxnKf1-goW41JBEl+E1Y ztqrwB+Bgj`4(qG=ISAgB;mr|C0D;zYye}1s z@r)4e%M>n+uOYmehWrV2$cLkFC`Pet`g*YQ-GjrGRwHja@NBC>8)fB~Tjb>iB6xus zp%cMN^q}&|pq9p>q4upzq}v#&tEkNuRWemVU-_vzYSvpp{d2%^MLY!pv=}7+%EZ>L z?!+d07@lRZNCCxV*vehAjQJ}=-HCL&gPG1>6KVrp=FK@-n97o=J-1Wa^nNkbJ6l{C z+p~S^#&meARkQT||JU>*Ai_XJXSz>ohmep1O%b#u2|t@0F=s^jlCL7(p?)O3Lh+*lY$!M)B23H8>i4BDBn$AQ{$ zuw|hn^(9hW&_Fn8VdT$7;sewC`IO3^-v5#@%cBBQv*#|k&A^xs@r?O!A!9!JKVVFE zg<%}9#LNjSXQsl0mcV|TwY6|CAPPhS)n7O=&Z5CxX_DW1A3%>P$Jt00qQ@LLn(KF@ zM{kwJc*4nS5PMKC{-Tk+tf3Z+$r(Y!bD;{OK*k#I=m>%dsEjV5*ra6u;Vd4CmfHxZ zTFe0U%$W^jYVZ-%c59NthMfZtUu`Inw4N-A*045;DT3*1Sr0YUNwHk;$zY2!_p`!Wv5uI)r_iF*D?9q%B*>G8ON#>4&@3K~(z*!e$$iFwI#R^R7Ds zvc(z|g_b3OW>!>ZQ`le|q=~uEV*u61JF%R$98Bj;X6O#_tp&>hepOIZ$>uYa9y3A% zBSs>=)s8dWwFF*F(roX?Uzd*C+V`~GB~>vIHlk?1=H0BXKHOu&*Y1^!mTc;-Z}+=Z4%+-6?GtTbRx{{dP**l9c1 zg?E|~R1j7gTPEwsN4Z6en3SBA6yKU~yv;(AK>y3SYaE1WfHs^uY$itdx;QB*3+bs#cLr_w%QIzvm;{wMt)^%S{UUdgB@?Jjr3aJliUvM^er|y6|V&z+S&XD z`V%v_V?XpIxVZRohG?5UXvHn`@1k{@e4zFUdCR{pf`d%fI^SUMh@}R}e{l~WU+pCv zb^+rXtVKLr(41IvU3y~%Hh4?D)tR+C1y&a0^1;!_;#*JakEG=^F&HHJ;0V-Zy`NiD zND0POe&%W6GXH6HnLjMIGjeJw)YlC^)cv-S4`e4*Yzjr-j2{b6Y7Hr?9+SUoFao^) zBxjxbkRG(nrH?6X*j)OQz2C3RC4Xi=w<*7*HkeE$&!{*Yk;h?AIF*bbwwn=)lD@O# z;G5@tT>hy6S3{oSa5an`G+d3Kv;kM;?EU`XYJazM$5R_jxOx^2%zNcA`?x{*{9gHw z2E5FtYV?hl1+3rd?%N_t8}M=jd%u5p*lg}D6rD(E1By;&@AnTyC+;Vkby6ElD0-fuNZEdoJZ4{AC2oCM zzRrN0GpH^dIcKrXtH?Q<(gx(5%iiw~a-uU@MJuGT(^tVv)|^PE!pSqa+0eMXouvkt zF!RE0W%9G~sC{Ir?q}tv3`n__s?m}16V_=JDc4ilfRr29`~5@8&_bjrk3J`lS)eO5 zMkM@n(c-rIX>XEM}- z6FWj#JasTG_Pbw_?=>K*>}d{BL+L@A#)nhdfT)q|{r(~9ghI|@Pub#{&Tz6b6ffBI zH?r9wRJ#dHzfjq1@`uyP_f-mi?-%l=2DHqjx^()P&$_MB&jLyt(6WfV-#@e%1EenQVjJP)FrAQ6*R5H1-E2G*HYczghNF0>-NA>#+X_Dm@fjrQe^EWevAvaVWxCzk z(aKvL*}~j9bP5(2iA^}xdXhWdmTRL85MLDz>v6U|Ax_{m%v)^DD^a4Eoaf?N?eNa8 zRQX$0a5Jb$3(k9h7#%_&*$n<5Z@(t*G;r7RM6Wt`y+{vve~_2yaX-j8jh*R!X6-TnYV1t3+mlTo(;C?n0kc}V*cG)z=vbOf zV?4Eyu%+RmsM_9sl)?GcmM%CwZA2wP`;VtCk#ahoS|7HtP#4#SHitUleZ~`=&H((j zpSKalxI7bPUCYg5qxq}bpaXmqpJjKPsh+oIO>Z-j|LaU-=Ez^8{#SM@$NYYu4-$R% z_ohYPyk|H{Kb#&kMPnhQ4KwOu_J03n)HNbSqxAHZFdf2=AQHFJ$SSD*yhzY+@@rMq zm^9+RL-$qH*z$(_fWZg+1gc9H0c%*t)d_YTYlQ9te&RE#5BSNHYw!U-mGbt_leefs zbRJgK&H}ZGSZZqzBO|+QtD-vgiI}S@)BU{DkIoO=F1WfMAuR2#)-9@-oy1mQII(XI zGsj#Z1mE&R5~Oc0S-k7QQET%$Ha-)P!#M~>PU>a@X5^&b>{e#JEic)}#qbZ_mY*^Z z%=J`_PB1sngT_fWvHEp_xkV$G+bGvSFn3Vi{t=AV_N2XcO;-d5aUsWT_8EOGp`J9S zWEtiq9QsSd!VaR?*AR-U9|?!u-<(Obg_9|Vf%jA-yDj&7i<+Dqnl)EwVGA-iN)1A2hrV50lZbWnrNT}l>|^Klsj0$t zlr)ATeVZ}Car7o$PI$4vVb~YK2~cy|Vuw9{S$v4 zT8~+c1LvYa!7_vsR&fO;)ZS#+I?{+2P6V9}9OA1>+nw9;H)L`PSpjY8{$~(Tv50kV zY7s1gqXdEc@~rCN7N)!$r`4oqWq6a57&lA>S$DH}ZR>;osH%nNeK8VcJ0k&}C`)J= z_L{1=g)+kqI@&~t|HTS!=T{%eGhBux+znKxJ{{jg4;nq*Lg@fSEl;yx#J91=Z9)*% z9-JSzgP!t>y`Qmyk-k1yQ|_WPXH7BKF)}R1*q7+jnT5f4%pQG%rBW**h1BaX%}BWg z`jDn%y1Op~OG&ERO8n_0h7*L{k(3FR?mmpeU-8Zez1D|TKxG=sWd5&t#(`y2&(;4! zo^fCqm#l36vplLrD7u|_0 zXJ}Rh42*ru+G?{@Dz4~^!=$~{dX?gl5v`nu*w63{9O_iYj83&aYT8ZwN866hmN6ezpKwLt8^h zi{)Q#se(hi5f&anDCN9x%5-wN^brI$p9?|wn~3=P3<3fDFFX-Ihl#Dv0~9qf!@mtC zJfve=QfY0v582F=<8O^PB!iEQ9Ep4RQDy)TSE>m!TyS#wq&Bu za`ESFfgo{M#d<4xY?P-A;v>Sd(g8+U1zek9sK914huo~Y#Z2*@75z>OOed7p^ddr;^+OCDw%=+_!; z1*WVemF|l5?0E>}%?UUQ`XdBvwgQFy4u{65U9tq=UYS#RETaB600^wal`9DUz%i2O z0JsM@$?tU-M!9G`g^#p#$wwrE;ZN_IHV1sZ}V43Yf)VAL@G`Wq8Th&Bf> zz(-yaHMFF7bvWLQ8$pbM-Yn;nA$()yl0LMiD}g&AA|0VkiG)+PV9MQKHNe?GYY2f^ z`w9$O`GsaajtGFHE#n;^RB1fC)oCw*KoCm^38l0?l7z;c3`Lm;)us+1|9dO2RIpUp zN*iECO>~Fi9R;p4`99@zd>`PbGp?{jFv+%MAk-bzHeUroQ&?}3_-o-V;ocR{Yv`>V4Fd?A zoOJpz%3p7b^M-(@GMqHo5p>X5*_S~Md4t1m&0kErvX~&wg2eW-aFp@Dgm13j>fyL356oNtZIz;UP zoN(Ok5I?4Dr&tD6U6}~BcLhP^z zT^v@KPC6OW>_Pd~gs?qt+!SABSbiha1)7tBVr|tV@9IRP({iR(F8xk$)KMxnv+nBI z9I0s})PPM@Y;xg+P$n<{;!x2r4yBxS^}SWNYQ=KR0b^}X#F5IqRhbwDK8Jv;dzrZ( zzUBy`>N)UVaaAnb6OP+hMLaDLfnhRp4%_e1LPglST@31igFqETS1QgtD}$23o}r~$ir?W5=yoq(53@seAO5UHsgqzlYuf6iG@W1n-jKJ2U}8UfK097 zlkWeFd*-#9y+}mZXWCT|9_To|$d(#(ol&U%1fX6IpWxkq7tS#Zd z#^{OJ{U{gY%3G~Pj<)HE5JKL8$zM%NvZS2~NgAYWGZ3By7q8%A8(S_euEqr}(S8;f z(c+*ws!2JiT!>B(?zI|PM4yCbfRlN}TaEFz)(L#edf>W2lFt^cwjk=^Ki6$7UNx%} z0xd*{l!avKU5AYgOFckkPh26RZhig)nz$Aegt<(C7ky9J z%r-HM^95Z7D8^lRPqpKwq5**{<`)`0zRPS_3$+s*W=Qq)_zGc|J z+CY0Hh0+;2lkxsgpQS3T;orY(6Wtw}7xxA*LlJ;8h7BDA&xTRf5}GQkeTdD{pB4eOO<&o5jMZsuv`H4C(@8Dr;On&8h7S)?6%BmBCkmY z%?}4HaiA*PXSuKBty8C$3r58R&_Vk1MJtp&cQVBg6Sjc zX8!Zq-ifCn?4)k^0jForcJpknfheg@ru(*rX@9{XP+wUM?y+lwE)GkTSb#$Sm%-m8 z1iApRIkzl=s~Nd%QKS5!81XQPIdND`3^xo~Hi+{OxAML9({dKkO-EvQ3y_U#3a>dh zIL_`Qmairm?zC1HuxpTVSe6#mq^&JyHRp50a{1 z-9R#oy|$RDOl06>=fL@}Sy>$NCY=&njL@(2WroEu1%GWM4$Vd&=e2o>)bc$KrC7vA z8*KV&VcYDn^c3)|3w5WRBpJ>j#yhd+Mp}s2TWBz0%MfyyovKjrnngfMng1Q#afZTCF6*EKB{euq z)CX+yE=t^9XntMpCot+ZmXKKe^_b`#ckR4@k|0NAAq>zDX*V2BGJ-vQv?Sb>u-^F_ z#3B^O>~K6oZ$-9*loU)^u0j7>FLs*hb?dy)X-WAh<_vbPX8w)rWdjlZMTp_y~l> z+LLN%hU21W@yYL20|wmdEwzoIEs3t!tZKOB4C0I-x@5!4-li^X8K~l4s6pFcUQ@pg?0{Qv`PnIjPWf0%FPArE!^eAJA_hCvzTHfjYQ*L^fDE zb9tdzI=RZx;x*hus+o9SbP(DRAS5hz+sM{nYmQ<>kDxv*fVNOndugHT;QS9<^rfST zHcOI)>$k)9667z%%_mG0f!A8`UqIBK(AL97?5dcxKJ{x zEFila)v5bJ4q$Ll3Qk5w(#^qO%ONKaAcjJVw0h39&@O@AAjUT;($sp9npNBi$K7~a z$in?MC#b1Gg}_8-8#2vlCmr2em*}@XM}sXd)?zVw)sWYxz)i7@;XCD?EW4E40 zNA34?idS?(V)WxGO?z4cDpJurnea@=_E|6kcOzVgJrJ}8KG5m5Jo5;>o4nPq5<0Bn za8t%6&52Z`Ph;P`$62e-!w}41zExOSI6BSOCz2UUdk?M&gd^i-XRW%P{DG_~4gO@2 z5XJov?nUyaFY9sK$J%%nXz79*K-$TK;;m2jSnsg{NHRh(SM;&AIQ`s?8fM^t5CA5CI6hx_9cM#R1?SOSX;?rfh+zny~! zNvPV}1Zf(S@nt3SEpZQMJzbr~*1CQBA+B&U2D?O1h=!u$olIKZm5~ks8eOxM;d6uI zMhV5SvUDyal(0g71CGh4aomJO)zR@#yhL%w;dKt5CemgcHYwo=XB%~K5WAEpZ^`D4 zRwtqm-^z5y=7>QR%1;D-SOalT$3cJsh^^LcamP~L;sk8!+cUHZ53Guj118h13bjqR zM8x*o?Lbn1X6+P$%?#aEZs`f;TL}y32HFu&DI^QAj#V0-4XxRG4Kxr3VS)Vx%#$K1 zs##odjb0zK7ub-SH4v2?i&~iN&=Ep3Zwk{bPT3+%#ps$g^?Pd*;Y|*+9D;Opg+)D5 z8-u;XWFoK8pG5S3H(Mr8t zEJi_&?97XLFP=?*9AKaZ2!w)NrjyM9UhIK*0K`GBBLJ!}RAw#=9&9)Q7&ty10lMN& zS``7|DTR%zP9cHTM65f4^E*Jg13n@dOQe?8L|CXJBT~#b!4TU8Qp?@&Eow_f-{&M4 znqnqUssiMF4i{JlIR|ROXWZdk+__|45!2Pkn<6O&%f_e{V89~Qw2MtAcnH`dInc0Y zd#ZoWb}I(RWNAMqO(FB_0r?szoOFIh%lcL&JJKwpQ0Cz@8IBsj)85g_29U8#!rEcq zR{?i{w2eiUrUC+@Yt*8FYiM5%d(E`9f<&GbYy~KkT-DW$4r=S zjPMAk6A*We1Cu)eC|R)y8`>$_Y$xqtKl&4B!O7#KM$AkK2(?Jd2I;l(>q33t zjZQ}~8tIDA)GF)^R^U#nNe{xk*=RBdgUyi|x0RQ(e86`V0V1qg;Al=Z}&K7@gxGic@dd6_Q@qowo7fs4<&6OwP&;@CWM<`7mhstm#6~Nry)G z8q$dGmfz*ddRK?wY>Ji_ih5V8LkJU!^44#CDn55NrM2JygaW&;Q7o(D@9bj;IQ`-M z*(dfihBcoDa1C5YC@KUv!m=VM@cc|4yK4+Za4C*+# z2h9-}>NKLMPGCA0iW1(40}!hHODN8u&X9)XbUfz2j2kF+RwN*HsI3mSL#Q|yP8@(B z5(BpPlrxtGi|s6#fC5i7&TD%uY@V!puZ{;!Z~x%mJRRV2FO^YS&mXQwqP8l zB?J+JOQ*m%t1FS7Ba43-pq8H<2b?$cHc&Iy$}=f-&yQc~_Gp1Ym2D$$Fb` z48#&0!x2ucH<3v8V1_^d8wbo}vN*wrgXq><${zHIM%BJSNgG?C9a8i~H2S2Pip1nM zm;(j25Q>*Ev2BVG4<(>*^Qx$c-N>pogLEpAA%&ytsZFtPGPW4u@9#Cb8hC3d<~749 zQ$mF69&b}5k+Kv`B@L0i=OX^1V^9@e6GoStL=1h&fVU8(%xQcRY3l%&rA-v!sH?lz zG0KIv3Clg=)chbbk9o~JSOn9oeM9`mgBG`P17zrpb``wMz<6Nt=PlBjXPDlCl`JHK zO?k8+PGOo0IsxrlH(*(xP0TNxn&GWNR7F@I&wxVef<+MFVw_^kzdZEo|d#gyW}eFxoj$2_gb=Ei!ZqF48#OZ(5J_82JxAY^r}_ zo<=zIdYcg&)Z#x=#qmOGjy(PFgi<2g8LBd@ZoX zv$dxUM!dM?Lv>XV!obGXCdcz$&2|v{EwEw6m?2l(43*{J#Dfz9hM~z})weQSiBl+e zEr!8})!&@x!?^=X8;r%x;Jh;^T7jv^vK7qD+MyLi&DI;NLIv7rcknf*`$UI%HJLo5 zC4^8>IED)wvQywXJ*t{;X!Vu8josY7{7NSau5EDyZ~|#z`yZhTZ3fjAhOadohEJ_M zS$La;XQMTAde&iU%t3~ETS8rtHY=(aOt2;o-P)1^fMDaZ@t{pjy2_2{99?utsgsqy zg(4qXTG+f5bS}^yBiO;@M7nX`3g_!%h!*K!7cYcSILpF6Bo@}Zb!~=L10lBi`qxDI zY<=j|`N?qig^p8ga04|-1ou)EY0HLmW9P#FMi@Wcd_91`#oi35z@VTUf4u$aCyJ8W z*=1ws!*zlV^iE;gqv5b+qqkXo7jf*3RFTH z>q=~Jh`5#+1f-g97sVuS80tX)qAf`{mhrYQk@vB`CEOdaF?NHfI>Ma}i)RYGsaj@) z6AsSh^>knm>;*nuF=-coaDA7PXoC2m2un7+`?37qw)f z>{dPHa!p|hkIn&unLU8ki1jHKM5hfo+QWd8$QI2QqX}F#T1;Cil-`b8qG%59z-f@V zB~4g~;Q~+VBbK_2gMx{)Vaijvl2$c^4JmE~SI4pEFT$J5;&nZ)PWE3+$}V8 zio=Gnk)(t+dC{Vdfv9oU;}S)Izd= zj|vVTJ2WEDl1R)Vvyv5YIUi^AxAej{5t7p?wzjX8thf#v?Zvnu2mB9tWYrRg#T52c z4Mf73;n-=p;uh>6M6fWR<%bZppf=pQ?bIH42ZT3RqXoB5Z(_k%xZ#1kDzphgbtf2k z+qQvm5e~)iOeVEMb=nkm22&}{r>F~4J9-6La1w)p(pjO!Irc7fr&o0)5w<1cYr@*o zSuan)nJ-UoS$FGfw5gDGOPU~qaV-i?;aQJ2cpn;RDh(q)>y)}cE?6^Y>J!Z_VK^K) z!Akd7-7$x%iYXEX4&Yc$Wm7bVoIuN_a0)9^0VOMQPO=Y7;BNtmClZ#2t_Ky4qo~!| zh0(V%l8HMW1G0m_ytn!aRV9Ij4-giF4=-%h#hc?DBkNd~M&Wf1Yc6jqRAtM{w~Llw zr^B8S03g+8w0~iuQMO<0U@)w+i@MBblDWhAnl$ajpkquy17?-gLPNHZN zqpuMwf{>FmTn+npUY#;-J!2CHj)zVb_|@>_wLBI=;oxCdaI#HclN&%z%~4p^a{{hp zz+<6sBQ>OrZT8uWkbgCiYqwxKTzRYA-u8rMY%<@hs4qhTP-MHcQ(<=Xvul8Jtt)?(*1-f8LI zFT_V`9Pu!Ha-@UNq|2i6N)+&Y7RUELX{ zEi+XK7q+6P*2(gS`(LmwwseL7fQ*BR4+!y;)dB+sN1O<;CkFp|x>VXSbQ%2XTEb4( z(fZbRr4#+unys_2@U4$TRinNEldAm94njHh5{P^ovhF(ba(ZxJlH7)@agrYd1kZY_ z@XjW=XS`E=I=iYlgya2iMehUM?>Zi$A^KZ(VRUxr{JHbz;jBig3kSP5h6YU6t9yE| zpD+-0p-fgw7g6~yP+qghe7RfM*&W<#xI4P~cPOFX9le|$w7a8gDV@7Jy6$)C-O(#4 z*Kl`qBjxSi-O+=!&Dh>uhRLj8PfPsq(S)IZsn_<;Jk%j z=Lh3INa_RSFleE8@E*gUokP{=gZ3?Y&<5>%R)4q`fw@xy(F?Uf+eW#DLA#jp_HWSO zcsMBE#reR2g(xSdB++c5gf5kBy^TnbvDBrV4YmO-s(W6gH%zAf*1pK8y^ek)6k(pf zx5fa)+mh&yS&H%fKgxue(0UphjK=E2y$9i5>kWnCM)VHbsg4GYb!kLdu~Z9eR6b40 z+l14vN`gT^WgMi+#g{#K;&y`c;o#4n|JIYD;(= z9dB#1rcUUB`H5M06wzIkpUsRUg&Eb!3B~zFDV#It>%>{n@W5ybW5oaEtx`qJPQjtE zw;(hgt3yy$(Vpl_g=RH|HaR$YL5Hd4uk{uBCirU89ga~!Y(mE)GQxUjjNK;Mf{$w9 zZir_YLh4!3xUV{$>~UJ|BBVHiVG8^+Rm}KSVgr*iM2L0x|3S!XiVSFq9MUAI2jmRIEosa%ow;8%O+6OV6Ffpf1>Z zDc7*}OH$tct^MpSVB{}xv|X@M*eEqLzECcB5l+?V9olTkMI!sKZr9Nl9YX6zoxUei0z}cmCRq?Q z%t***F&Z)w@*h+}-u`VlxUYnK*g3(64TStO)ukITo}~wkke_Fb(2W=`YJ~hU-tmB~cAXzgfNI#$HO zTR0eM{W^CS;V7AdjKdbS)hZ?HX;Kko(+8Z72qR)lZlV{QzQkohVXJE_a$=5CB!xrk z!&zh)ChR-otqo@)HX*F)yJDe`gKIs4zG?v>#O-K-1HX*|rFz==nh-9;+TjD8#pzzQ z2cvPFIzWGp2WA-s@Ij zl;Nh>gnI^^2G$QMM<_Q-B_ARQLE5P$b}M@Xnhf>Pj;wfO>tRAMcE@PK<4;%#p=1J; zus%5-NAauoky{#?=|V6^N5Vi8+|(ktc_iN_gPM$G#bB;VgPDp0k_|9sQxC!yF6%rk zX%-&Jl5F9@2#tk>q!i*OPz6s?Oi9#nOCYeEIfdH`G{tb4oHqQy6qw`d0WGd*G3lAMKT;O6gI-s z>bQXRtgyMZ4YwY&rQsNAFSkjtN2E3QLRdT6;SPq7lgTO2LWGH{Re?1jvEU{i(FD@K z8#PQ+VjvAiCn#p^7oV=gTnoP?`!U7tO-G@by>T{57{;XvDxDo1h!nefix5#%4ZCL} zPU!9ifj^t7@%bt+TFg^S3_+XH{|A1H6!OPvJTbGtJ5Cfjpm0hjPP4qa443P5Y)ClW z(QXQiY8Vk;eLT|Hm0KKJgl30{IL5rKh2#nK75;SyiE1~pm@CN6Y=sg;zC*B3rzX$un_%F zv8>QOsGXyAHdX^K4EK(EPbJv6$6jn7uX|;=Ilhn-$|~s6ss!R4#h9+9(}Tb$2aOit z7OW3VI2xAy)fDH)+9=`(peUpIA`0c+VC>2ikEm015<8rwUvw&cE zSa4~T@#>$fdzpE94yYI5@{uB=qRqCV6>RTH*dbVB6A^X+gFdiEMjt`kW8(8ScPqn{ z;DmkT^L8b8Ri+$sd~_6krZ;03?Odux=kxRELF4laC|%Z-*xZ|LBLRt91)~>H-rzY} zK&$@R)#=Vo8&>ix53w7HbhL!}qI`p+-=!v)(DK%9<>l`O7w#ikj=C!N8-w_}k*d+r zax*<>Xt|ZuubW(N*Tmlr$~B0;J1KAQ$O;OuMNYz&QVU)XZR(}qc1wJ4R&3Aqt(L3m z;u@&lJ#CI>Cv9EWYH$$|&@l&U|n0KHz|KoAPPh z#F_hQaN`)eiUi z!aZ?*CwLG?qsbFowN&z*$i*gboNi6?wb23F5kjGl7Q&30XE_g!rZ|Lf(oP_VPgxFT z+TYjd);QY|{dacXpF-$(G@E6?h774a2#7fxxBw&_Vf>r?v;rGt9mh zQmwj}*+vhVn7NqJhS~Q!ls9;RBA8DC%h%(;QoA~92x-rcgDnR0sBs2Xs2L_qy^9(6 zC&6+1I0H|p z75yzGeVvHaoo*XQ!}W0dW5#0;2OMxFYOZ!;ns|lQ=CBXtiHbPoH>odENr2fR3 zVw~CEQ<-n*)^Ho{4^14~8ELoRzd^Cz=o^DSG2rlPs#nM1H}s&Q=74vQRIxV*#GDK@ z+Kd=aCH5I|E6yy=AYqM_A#JX3q31kb7@{~L9s-$=3ZZzMBRP6;q77$ab4@ZrC^*uF zyG{&>cQN5arv-NGhREelDsAt+SRQw@$#cg~5%qB&s7BuTM>B=*?6^62g3B;G^QlUG zcoxuuKZ^Ljad`Dc7qRASO2pDVfPVygil^zA^FZ`SR<0MOw!VSr(e$8k!m%tJ>FWb0 zETwc&2afSYD_Js~jIA9EABcw=!PH{0yeE6sUByqS%4N4Y922g>iNw5;o^=b%!r0PF zrJQy_DnrRO{+tCD7LgcO_rGiD0pEiZbdEHR_VI)g(`di1a^$d0h-VXy6EkAF9-Hl^ zk=G7Z6`t1_ZWJ%dUAF~aH;nn|RIxthXX*np5Y13BKm6y=bTU zBF+0H7zy+~)^FpK@u5nf%ZBtO6Ft4D4T;2l%@}tE?>CU=D^#sM4!@xXO|-n0!*2Aq zEIXb^g$E~2%(ThvZ}Cfu;#{w62=b3qyNMt_Vu(o>*iwSge<3&e5dAz%!h9E{-lo*U zlsak;elm|x@>EJbN~v#AYB!~Bq|{@S8u2)O_E2gOr5>kLh*EngbpfTGpwttTdXiF0 z_TuL$O5H=Lrz!R3llXatQr@TV^DL!iJcX^M=yQ}@MVZf2Dn+RmDD{0xy-2BtDD@Jh z-lWval=3`{pI=ZaNU2{^Y9*z9MX9}%dWBNcpTWQMA=l%h#DI^!MukU)<1QR)LqeVQ-;@$oZ`wTPv0ACI=0LM(6?+k;D8GT&KZb~dKct2 zqA~&-VWKmMpy>UpLoxWqeQzLG*M8YB;^+tWWoxv%YIRK|Z ziB3jkQ9u36M`m;({Vc{$y(@YI{VRaf92`6P{C`EX5nl5x1nrVs=rtH-A%51NxC-d{jay#zqHHim}lIN-;JHQi`$Bd`dAkI+{|9jh0i2u~8GH7#ppp z6l0?fN-;Ky_YY;+H$7#lrIDaJ-m zQHrtAFDS*>=y#N2Z1f(bh>bGQ&nU_G=wFm#eB{}R6!B4XD5V%1jiD4{qbZc4gWJ)W zlwxeOh*FG=mQsqbQ5~fi8?{o3vC%1%Vr@yy^DKHc5O>!P#FU+>FQi>RR&+<9 zJZd-&|3c9U^}zt{f5s~r@R9?wM3=E9q}#ym>a?>9_*2>CNlGzxd6`m-U4Ba`#x8%P z6l0e^Q;M<6KPko7rRY0IWf;Eu}1c6yulsDaH8ZF-kFhd5%(yU4Bg|#x8GCim}Uwlw$1iH%c*f`G!)AT>^I@ z#n@#er5L*$La7Yn7m1RLU*=MZ@yn5vV*FA~DaJ32lw$0%mQsve+9<`?B}OU6E}JOD z*yU_WF?RVjr5L*mP>Qk3HFpvJF@Cv;G8w7|)cj9pGrrac;5I-;E>&ase^>Hs|XxU%Wd;9>qN9S9Fqk zL>t&qnmMvQteM*4p@F`(D18+5Dc;?|$p?N1>GLT-(D_JcpDRc14jwW5+w>Kmd;Ff@ zISaPwp9P~?B(s5dcrz|t!~KiVOQ^v2@neK{<>SGlhhIr=d2ru)EI4P)>B!YQ^tFEA ztB4Cfnf#k`ktD+kR~k8dk4$Z~?!jzB4_J%s+n%`-)fsE|(&BM8&>4e3yZ;Yk$;wiu!oME|=kDc^n~ zxOn2@)K&vv?@6$8O=2XXoVqtSW~7RF{xjw4CxVj~upW;tq#D4>`e#nk(GoRQpd9~X zaBPN^1SK+DW#Ql(#-<4#|0{$Tn*Cqk<3JI8GK3uUt}Q}dz*~(__XjD)N(4xW{uWgg z5YX+UXfnoU!s0Mmz8Uew-dGWk0biOq5`?4j4K0B*)<-IPVAbqNu;oNzedHTCbCPO( z%zd5zSef)xa6*%j_XtFB!|X}SinuT2dC613nx$obL?@XvD{2kpM42XZ+~FQg+#H0@ z&L4;hh9vu3aQ=EmZ9y}gmd%_rZ{CvN;nR;?xNxz6gR%RVeZSvRT*8$htj-7{H5 zGtfYdIAr^ zE4!Y6;u^YcVS*Hu^D%YCbQx>H?UJsKC?P>qtM6%zbNTldF7Re{=DH7#ryqY1vT%iXT*0}qY zcE*dl3nC~1|F9Erbg=y7#QuG{KFQ=oer$k{62CrPDdgTP9iuRx=o9N3e z(JdJwcT1yPqd&3_@YU0TPTFk|<$|q9%1M;8m`Y2HZk9IMMsJ;Y0o}6nFbe9rkM>mP zO~L*K9M7fJ%keXphSZS`S)teQ^emFnBc=wJ9w$eSQX>lMRz2LaKDuQxT`{DibmjcW zo*1!8B<}Yg*`r-zs%PR>>bjy^mb#*#uB*Oh($zwvu5k39xpSuD>3K{_kC+-@dZ?~6 zdX(RZx>}^`iuDI?pv9^fuNdNuuC{z^&n=g=PQr7NYz5dgfy>V{HTcuJGVv4pG}oH~ zy^Kh`=T3@RMz<&FgR@d5 zd0mMp+^=gsFTbcjQitdg=kDe21h)I$qwS<+kISvkv;t4~;abBzbpiKQjMs zcAKh~RL^=5v*YwqYt&1nOfMbJ$G3syL(Gm-j>d=bxu~2Kx^mcSH%&X9g_JA&oQB1#2*NcKPNF)lHch7#)@v)lDHCEc=W@+lP5+LVRna*KPD zO?%94G|FdzOgjaUamd)OK=o7Fm3%X?~FA8e%sw*@PBjNOg{B3EISHaBk)Dbdy zbvR28d1Oh7wkJz2uUS&oiz=I>M=v(+(xJWQ=U?wL#DmI0)V8!@CwT1Z`0Ab+{UF)(gM|>(7OE7r6hbrQhPfx*vhp5< zf42os~$un!&q&r#Ii(w~gP)hE*{{?%Z*P@p@DO>Ks{; zA@(F|5DYL&Vw?@4ef8TrZ7|JMVPQ{oIHnY}wC7LykSw}o>9-Wr{MJ>NY^szQdzMPx*WO$s-)>Ahe=YO1WQd?xBOMbki%h->y;jZ>;Rt8Ap#P>A)*61zNFLW-VaOB`xP zODNCa#SGzokM1Ar6ZO3xNa}J7vG9*#u>|d*&tK)wsKyjKq$i!Su#pju`B32iPthGGCMevX%N;3@hj&j*o)wW1;iC^ z0Y(jHBi7=rbfd%x)*;IipkIV3^`Qiaa*3&Du!>%NIqa$WLP1^M`BwKydy`7gDo^P8 z#>rmg`u?w>zEn!RDV0$#rUsaL>JS?BO1|h2@w!8>IZ(p>7rjDki!;Otxpe!-$)whjuct-e?Pv zUjeK$r~YCRJYh~9HyH+*Qd?^$!yfYux8@f?ra77Px*DdLu0g&lhB#j<`o$%%z!mw0 zyy~O&?nqI~ivA!PRateBZdq0rDX0~vUN^aDFCL^Or{T9QX(^-JGnFLZ%}cW(_fPS% z^;LX)pjKW7Pn$Z`qA$`q?t_hb2*{)zWiKHxS9C5oM6+o zk)O*6b^bci3CoEi7;5=eA*mCUxne3~q5qeK!t>#cuYqUAUmeX)eoul5Lex=q%m@_8)G~T~I zjrqbRu$*Q~{d_Mao!*r??xHv(NH2M3mX^e)NGIF!z?-S3U%|z1$?J<@;W?#mc%bQ1 zqA*8;Ap7ZpWV3)ylnIg{CP7|=x)bJ}ByU{@Gs=wq_#C*6|P3-Rd`3i?z197u{z#r7Pm=5Qt6w=@T`^9C<#o`qkw$$wh0 zh5Y4KG8+j~nv3Z=?Y5b?avV8&9Taqw$(DLFnH235CTng-lPL;b%;0k0(8=!Eq?Iqw z9@l@-AF+dpAtskojcFV+H`fJ`rj`R)aU8dsgtW1oA{tSiFms5)aBv znyS8clcJU;z33%;a^{6}OX?%k3n_?Rn4nJfXfqXK+$?-rLC7XjyM*kyGq#7@3!k$z z>7M0YdSUTYt`sWAA>Y#XZ=NhChOh9+j>d+1+srDm&;_Apdv%x<_j|OW6zvpN{G>gt zsJw(%Gk9jWUKq03vDdvJ@l1xuJyWQiExH-L@U^35{x2cV^`nJ#)OSo$)Y3Xz=rb@M zqg$3fMnRuTIy#y$HZ3V7eMAZ_@5nOg^`%87WYulny4hUL&GN9DMLG+z2Q!!|dmrRB z)H>14YRFAD!*Rb%V#DVWy|-z%!LcjQ94pnL!f((^1-6L6CnqJP z0z*s+mo@Wpv`9WOBL2*cS#cL+xi(TRg}NOLVrmDz6txUuKT;N0 z$fsMDcP>ehH$ro^?CDVOKska+1gsB$B!m2Q!@3c7N8 z9hNF2ss*N-O&1V@9`I;TDcTtf`e}O_RN0AFGn7c%^b+ZCCdd}8A6BrWx*8V}vEjr~bT(}Fl&oRqwnYNVwN)iLxn^Q3pD^8U@csB;^Zr8QT*8ABm(=J2g+C3x9b8sb+;;JTxEqhX%Z0VY3 z#$v%e%Gwv%Qigy0EyQO|JPU^Bt%G<~wb7<~GN@L}gv|n?3f8F!HiSNC_9VGh&xS-R z4)fZNL}wsK6f=>KsLU1>y7NwSpdt*A>Z($4vNkeXZ^}=F&c!uSim+ocx5k01ZtJ1d z{Px06jo!2YQZw&73wop1LyoG^F`hLlWXlbn>S3^H$rOGTmCbJ579iFoV+h~czT-;4EL-zF+0wkwHa)1 zSt)0wJRqJ8G4x%ux&V=B&9DoM_e>Zurvpojn4N?ej6B9$c6jS#+ zT!#MICS6T&KBy^g6AZ}=`wQNNpwPBu$vjqB$pf39K#f`BjP{^9<34jrbqHFv`& zk!$E|`0zkSFZ!Je_vD1}5f=zP#7r0;>b$9%PbtxOBZf+xgD!o@;t*S)vD@pCIK&Vy zq(h<~g5JLNPJR0@#AQwLpC77<33T4n-sJd0Fj`g41fvl|<%roarb=09w-V1(7s|@7 zwrDzZJRQ}6r9;e)b0m!pWv(ckCAx6fDxSqM;V{Gt;V}CYJFlv7RMlb;!unH6>}tmvcjL^ zVpJxX^aPZ){Hbc`t%>*!V0J_PqrnCIJivWki(T66~cB@$_maDYYfdSFE&%kEr@{UV|22c;S-Ew&AB&Vjv-v+n~&x`pP!nzfkY< z6f7BY{@3Uq{zQ*mPx^(1^0c@106$XOF|Ar?!<+a`>Wxq)Cr%tXS7GF_C< zT3tRbQu%x!lMh2o@{yC(_3|1gAI9_<3dpV7;R;_X;1MrEqidOrJbc}z4&#ubmTzai zqtD0cCv;0%hrs7jD5%v>y#8K>4dWP-gf})a)jf=34c@vm6H>p!+gEPqwS~;`ndKH0 z6~9c>i#{snr~aGh5sxO4qMgM=JKNJl%KdmXLwL^Lh8(jt>?!JBP59luDLgYo?q4%Z z)r5;?IF~xB>TTtV9rcOjHMr?doZi0+=l(e0(P~oE(rP!+2V;&!x1^enj`T`LM6yWX>xP<7?D^{1u#yJL0c+b6jwuIkgS4kfN3hKdOt9 zZdrMCbT_1{HTyHXe-Sfb^;q?N-xBHtPG;31h1lvpr*r7OFRr2j0N){wW)7hn?T0OUV^2$}Ze-G_@>mQ69wGv@3I>IdB2) z@L%+CIq(tO z;lcS89H`(916}SXy@yBFYp5H1mk0k(0K+fmuG1UX#2p^IiwA#8!D(C|`y-F;5KgV$!d-U}?(o+Q z-O7QzN$fs|3J(1c)0UC4?F0IgSPeMLd;TwAzQ&%^KRn=83 zrlT2?uCA|c`DKfeqrv2deP9a;BNy+7L7|iN)U5qb0=e2QyGD3zZQVR&No93aQsYu~ zkrE9jt$6s*3ED0@JfseXW@*`#Y7l_~FmRxHQ{5eluhI^fs2?!z0Q3u;qVKv6z@T1b z+AjWI-Q4%?)srH_@F5DdWU}`F-fq6O%Z>`K#Suo0b4W@e-!#Nh5jt1KU3+?bow)!{!FAlmGq~M{#-|Ya_LVa{;a;TxqD^p0%vViV~a8l z6Pm;G8m_6YZE#dhWQnZ{-hud_pm1{6pJ92>I@0GLWZ=Ik>c2YSgLlA|j6^9@$v?o3k9qF-_G#`S=-RVKiV`Ip!kltg-#qUBi9+&wp zOvQgI--T-RA}OJ<$pqfR`Iy#``R~DWHPsasdkOjTdytB$A&1#1vkyZa?rk^>Gu106 z#@rqKN+OAWA3!~6d7s!Aa>M&@;V71KXv|g4CP$MKTX0LNl&A1!uzK*+K=h3zOxf&C zS*jg3Yn~zdtGd~{DeTb_FNp<`eS|&Qydy9QGai2o21kTVSn8;4wB=PbI;-njly&6g zBQO-fQ%7J3{tG(_Y3jY4N{k&$s*Xahe0DFvF-;8(wT&%HSWeA7rdBPeT3l6s6*UMu zpl8hDwj}*_m$0~}QhM?zT#8wAKL(@KyKxf?F=YR-ARx~kgGdDS9fMSrpU4=pbLNnK z#C9BdBd`X~ALcPHs#-NK*Krt#r~KwPB&m4~CZ~==IBtJ`oIUR)C)mI26YQRz&G!nFNxMLJFiOB$UuX3BC7@2!RBWA&@`8Nw{Y#s0E zK1(WZ_0ACOml72FLN(OS(tdR5*rMEV!%7Q^M%$-}E&VJ7#+0AM47-;cW1s3DsL|N_ ziy6Xg`%1rR_Sd8c9C**yYX4S@5N_Z_3#3?-f88#~HB1EWD%FKR`*gXH-B*o3{(?Oq zFb?^VKQZ<#L5=KhsS!dw$d9!DqJ-N8OBkxnFts#Huzi{(OXy26SJiO)pO&hq7sGTH z?9-~YvrqM_E{v!7XDs3NQ+^Ssgyk1A9z%k>(I~;56WG8$tx}Y*j6!$&h1<_ms*aX0 z=*vbZ4rm}o+gF5nd)c}R>_?RBW76wLz_oxV!Q1X17%vF$|FL!=_9G&8ef!JS z7?jA6hXW$)x2)BLIEsulBm1F_4E2pQ-2O*kb)g+awKkv(x?L$lw_k$d(L};0)V?Rw z$9_66+}^oLO)xRYW)BLg0ght|-memXmg~TbD&h7vRV#ymi4sffQ>#9OcIw$lRm1He z!GVHi>EA3$Pcr1p-evwt!{N@j>}KY-watDNeTAfLu=RdRcD+i%@%Uf`4#+a{eh&Oy&H@&JpqX5&3CQ-g++_ zJxL18{X}@;iC+16Q8~He^G26O6%CK-)Twhx)To@XBTJ%kqKXT~7nSA|MwR3j3@?o; z7#&p#*utFAxh2DLit`A(q-c2Qgq*Q?QMq~J^9qZKM-esvh{_wEQ#dY%HWnXOuQ@Fx zYC?V;Y|iMC;h+Q6o7gMAXhPJ4yr^Li4tWLB#^DV)e4(dnqO3s z7X^VaHgEK>{JdOReMqd4;DKNnl?RC2qQasP1$iYYH2i7&(EO;eJfVoR0JIVf&nbY=E{e(-HmnFr zje-ED(n7cn%^6xy$g1+_oYHYni?tSH!nA_ILQpwxd_if>P^d$Nc{xx-QB(=YSuh-` z5^yTXD;=6MY@{CWY0w}*uaP#@|G>ni?V>+hyM>nid1_mqIb|K~=~gXLST>9TiU*_!NRY`(Z=7}Xd_OG zylZTmFomWJz1 zan7F%CnQY~iYP8!!xa*o>ik*5o0u@hZcVPDIz<9$sRB2X1woic=+!zJ{WULpYU*KO zCFNRIOMQcu?)WNBkWBw zqNMZQ&?JP}PTTV`wgj9cKga+uvU6rUq#m)y)$W3hc;m~p#9AszW23{bsAA5a%b8+0 zT~<_kV4a%QR|ucT&Q2LM|IW?I@rGe?bY_OyK;s2UCS=D8iQBqm|D&MVK6quYnq+^v zlQkgS$0uO6iv09m3USkfruGkYym07>sPKali>VGPDCA35rVq z2qsrQhU!95LQng_uJyxRF-9rz?H-oEAP>T3*jsd~i)NKCSc}&{u$e}|2Du0Z2qxGx zq8fAr6*i40nV#+0{e_<01^5rae_rsPH~i=0=-J)(%emoCJOSMZ{Le7ISwl*V?A+ot zy!TtV3hr{ww}sVUSStTYADknI)$w2?tN5#Pz5)K!U}3g5oW!@jk)yHyImv>no%gkB z!Qj+wIanYB_df62)XHt`%$nwdqrK!{L30Q`ciz|O5hto*9&z-!;QNdhx>UYTdh7?E zoHzQUzKc%)!F+P2T%Tk(Ubx~rva)=inW4viV#BI_o8jkt-x3%@=8Rg5$DEZyBi<(n z_pqgs{K+Kwf(B%@uK{TYTZ1I7X1e2BUo)l?rB!OF!2m&Mv~5_!4uUnzm&FwsU_^F- z=sIQJ)2M#s3(y{D)z4Pb*Y49eLx{%#;Ai0)t}cmTGH-@reeIJP*NXlV@bl%ddBbyy zM&%TYUTnKZ5=2NSomiZ=*!DNhwkeUqL;Ej{Kb+y6zX3nv zL#c-SgUlC&={i17!%ty&=WoD6hY%Y+2eh-zh5sWR<0_~jPKmgU9S!dKCVC66>O4ni zJOLpjN`c;_wqg06ZwnL`Py1aw;ht|};XO)%kKXgGEQI4r_k63O%}^>#?H%fU-wbbI zF9Q?{QV<^f&{uV4zxdEMz)Lu_WQEv9_;$%pVxn-0K#9jP1TkJZL0lbXJC0YL^NqsO z1yK%kbK4bPe0!)RU3iEOgRuj3Pj#3OAQ0-W9S;T3+Y5b7eU)yZ$;?@s9nE~ix`MTe z_{0+>Buc&DA3*Yih-dkV7p!6ACm+kQP{ZRyv3VtPtl|Bl*cf7MQJ5Ivm0)AhrgeI; zxP>I9S1{VVAA*DMSE87ZMx-(5GK1+t1R6IKmRy81Lz@>Sk|<2BVhbhm64fF*a01Yz zqbzp!e?%3jc+4X)37@Y5k}iXi6-y0Vsj9eFcwZ-28Vs55F{Iyoofz<>w&4-M;t}C1 z9q+e5$9%yHcr%0-0M#ebwfb~0NW|6uAXIFLgdcIMFtL+xi||ejyg?ii+2JLf`;Yio znD`U=k-97${}K*`00U|oB|@ADHDK#ZsVZI_AzCY)1g|;Uv`Tn?gcyzdCA_bz8p*4O z%&Uk+B3)X7d-bR$Y1Lz8q*x`$5K@bXP+>Mn!e2&;lLZN1swHOl(Nw2fSLRD~9UoQ~ zhYQv$$)zsb#2L}z1feCKo}_E~vaV^C<65-XR1mT#W86PhRE36kQ5`WEFNA-iOi(03 zigE0T6<-&ux$f*o*A(-FktX(wb@sWApg3`cAmmc^7DG-BE96nUp^(%B@ejc|-@TBu z=3+;|ZYpG{UdVjM-X!sYAk1ev98Cco=1}&21{BjI)=@uI3=pi_-3u9zCbkuJ(L$nl zNG#I}(Fkb8zKV|~iNV;nmUvp&PD;%Zwz2{Z6q@NKq>BlH^_+WwTQkIg!uKYvUeyac z=jdEp^c942%yfpF)1;_O;u_LvM7Tx0!M!7~TvvP%S!A5?sZtjot}BXyjK8ZZj;LH+ zhENH!g~K1{o}=)XdTM4+G-=U1<@lL$@Tq#@RMbVr!f_=Xb(Hbewqi`>_Kag2#<2sw z-B1k2Co{z+D32qDmWNzYUyMMLIdURHN*Ygmxjl>pqo#`9aw}F$Hb*pLKg02G*jy1> zv6Lt zVmw-7R$wIs+GuIZ(brt|LuG*)iEp8+9CXF3;7VP=%3Q%W7<02m1G2<)tB>NQ(Q8>^ zS7cGBM)6#umAXcR!bKw=1vhUZ#t8`LG!tVr=RG!P6pr6-BIcnKg}PZtEC;x}sc1(n zIj}heYOZ@+LCtP7178hu*NoJCWHW2FO4p1~xM((vYc|9r@E{6gz6!@Jv&Ft>E*JQP za)4ni#7Sr+2fjgpG7ri@3fbU^Dc4_pT8b&weePP3#s(cUYqeU}icq*{wU2A{u}Ron zCau=C5<8=xxv*Eu0hY8DXQ9U&_>W1eT@}!3M;kHGT3vOE!nL=M5zIa!>JV;d7Fag+5j3K+12n z4%nx%;ZeKZ;uzrqV|=|gbfafEc8)u?M;~#L@CU;_?gQ9696Q&9_1vEr%BHdh;-!7X z2iD3K7yqBatNV#{&Eug^e6^pLDum%_;<$kwyF3VCUwpZfyPhuW1|Pj&op{4BEuZ3a>P;r zrZ|^}iS>mfd?^>kfiZabFtN3k*hEXr%N1K_iQTlslsvJvmN<+iDlvYn5t?5E7Y!9_ zVE^GzCwU3uHM$kU#Uw3pj+WSUgqVn8{BZP4F&$MeTkLSh{SjiQAiTrG-p1(P!MFgJ z^27sLVjG*-NJ~7eCHjnnF*!&6swEyADK2Il zRWeyVpc1VPJmd;Si49R2M<$npbi|H^;Dmu!^jNVz>Rbt5&J|nYuH!{fX-zr8L^uRL zHChb8yHA0sIdF&p2x-q1iLXT4(1T00g(9F!j`W}p`3 ziJwyfLczG7iof5;WEZ|&3iXL+oiJyu9w*k)vaXr4`i=)(IMqMqEb9cZ8DvqZb}*^5 z9x9-cX*5x$`(ORR>5OoxK<5SN-q-&|gTIzyHVv;lUSuHhdvLSV;mU?}%nC8U3rKP?x1w`wO zqh><8*P|S%x=s~;M~Apn-!SS!_~10Ljx+T~Ep_^Iv7R&azLwf(hFHs)YQe&@V7a|{ zVi-R93`~U%;TtnRghNb{gH#gDAJLU7=#Tn@YX++8Z>mih{>Iug<5{sGEH+bM$MS%U zpA)YNc{q9&w0ENn;ug;aar5xnSumI6+0)&#dpr*dWjx#No~^zB)rDuTbI<DjdGm9s(Fp=Ib0{iPCtW9EpbgtJVC?_K$v#na}Bb+qh1-Lvb@gF45lW!!x} z1manIZ64G%o*1qrzCIsf^(>|WoniuM?O_JaSOE2ckM=y)CHn#~UT8~rvATp>1(+O| z9bj}|;}^jpPZ`hy%R}FNQ9L7z!!s5F(G)_|3j5o^f#YzGg<_hPv(S{|vj|k=G^wdfVy>Ok$de^|?I!;~!_T@RgSioXO zL27TYU*L z?yX){lefBCjo!MxOw5KAQ5`+94D_N`#2npuXJw22=1hImbQz+{DO z^3_^PMg@L=PrnImD$lO!p8etqv4NJI=$_qirC3kP&T`N8StZs*54e=~n3P&W+1>i@ z4dtYbV3`qwZw9Od9^0VzSvi5+aXH&95qQ;VXrZPu+$7I9YKz`$#IMkjK-OKo&g8wd zPK*(j;B{-EAJDS4n6ief16ylZ`}Hhk2^9juIv8(S0}Fd;t6++x0Z-^aV84I8Si_lh z&6HKRL99)($oNorxg6=Mza@Slz{K$#h&q734NaViN4*U#15b?85~JP$Ry?txmiXN} z;47ZkNlSd`T`>izK`f473x}-8X&%Z6te}S`5N^DJl`xs=5)6c@I=wi`6Yq8+hVgEpgWtXytg~H(KKGtzxW}_@kCs={*<_a^!t2 z@uT-(aK4u7zp4yrXzYyGChkRHRaorA;zc{OiuBZ0sQF>|-R)wsGe6Tk|H=2on$G<8 z?)knSK$L0xpLEav@B^qzkWa%T1PAO8V>L&O2`bl7Fs$n=yg)c+2+vVM%{w!yaPQEO z-;f;;HLx>7aLYa8s3ihE6tAN9xg|c*C6!)f6Xf^tq@6H)(hx^IA!_XsQ=N$KJs~dd zg04v8@uw%m!rfqT4FRjNdmu{Q$IU-tbkt6;eF=7QQYgh=o6R`Y%-wVDGxnwzqm{IjH!B<5VgX^UqIA;h7WxT%?Ho9WXhTP8T4d4=dLLy z<$yB>`3B?5pNSm+c;*09M21J9&eU0-gP%X+2Kl5s8S5N``qem?)-TkOGiZ#T{sP>o zCHHYA$A1Y1){+aH$>+X=N~9%Eb|$}c2hPt*WJF9fJ_mu!&mgug4gcTHttjk}WwdzAJQu zqaaW%dNT5k_`o+}O`eE`hmeKZ1bN9>enJQ56pLZ_<8L6KI^yDQq4nV86E*U<@1P&& ziSucq(lLbC4f@Vd{P4I~%`(e*i=kr(^HaMJQ}tOHTyFKDR;7+|gfK^KXY`t*w$cJ& zahQ%6a!-PzzUIh7Wgscf;8Wrj;VQGoZ%a>u<*(vSr@{c9C&LWKK286YZxORh%cUp z3d$45Yl#akz&M8|&e0ORNDF^}VEh9w`vFF;JS*0m)%z-Rc04Q7oTdB-Gfke=-jJpIK}Dz2m`hj0aEsxX z28TasfCGyOKf&78AKa36%GM0m`dR!DO|8Znzvqoirs7wx!McT(_lh~M$1gCe*7Dvp z=SkOLM62cPG3R}9U2IJ9Xmc>BnyI4g3#C5R)^V@vYlPaKM-P(Z-1ErBSAP|2$+KY% zJ%^m@#W(ti)o}gaL_cjGWTC!Wuvo>n?#ear3_Atd(TPf7WgMLd57V{@7TpwsjN1f@ zi2z}+bGYNCXcH8?=r1uNg(k9-6ZfmJ{R`Lvcx*Vr!Pe;$Y~CWCeoNexUKLJxzP{J$&C*6e^H#g|Q6sexIn8;w>-d=Q9>@Q59 zg;%lh&EQqKJBq__Mh&T|P>dJ-EoS10zf+D|!=-w7=kG9-T1-pwTdh+p3S-B4zWxK| zMK6Z2{ijENh`+!h^|e3YB+dJ@uv)flM3~49Yjo0gxOlXSK#9f^QST6!WT6e5`Tf5P z%oFd4F9;_H*DUl62ZY{d0J2Nv%T7JuuJ^^NnmL}iFE+E@ayQ4J`{F3!FS9w;>k{7L z=77^cf5WoDeM~JOJrD;AK{(q>O2OR})fd0|KvaYPT>MB(#z!B3B$dLc9hUwBr#O-s zke<$3@DJECfdVaW>BUsSNB@DLK??)2(?dWu!^PfU`2`QfwQ$IbmPgoF-qA^W5@wmG z8!HeWdL&MR#X%<&Pks!1Y_vqbcXcui|NUdJ1m+7)yk(<~nL(+R?2%NB{gRu~Fqk#y z=uJ9$8D1zzR1n<6v!iJYAIh-quOLN}hKWH|Q7|&Yi9M;Ha=mBws{Q zj&P6&<20JDAp|2E*{3Gbrq{Wcqhr3Hs zGQQyp28Tk3Y1pwf(!P*WdvNNrgF&7vMzb2UxEPLwUeNqvQJM_f93V)BWxFmw3sOv` zaFNB_lPv#zJ-c>%lV@UsNG@prNBDQ5B0cSFmn$wf9ZD&QHpKMuyp&w`d>g zrEGMBRFVn>w2>R!kj0ux$BD{PnqWQb%J~$2s;gQRrvymB=HBQe?j9h;38zVs?7S%1 zx7K>2?;^_RjlPedy-^xDB0ArnUgj(=9hXy>Itp$g70@Q$aJX;P^8)D%4&xlFv>P2} z!sD)iU~S$CEew>tM?R5wYcDa~Z#99lz6(XN2KihNSoAS>nWc)f3xzW&H;#zl&tDR&*SbEW`Qfw$~tS&@KacC#UZ`bh-z>{;f6RJyj=xbhdr6?%+5aVQdUk4u~Wv@k7 zIhzmkoGZN8!O>7Gh1I|>MN8w*KOF1OvG+N4R1C%5j*)7xbmjR5v>h+_NwiTAxImk*c@*AL_(0cucAkjAE+eVlrr% zT0^fedum91g*Jqcot5_6sgt#=&MM8cnqb4`)mb~Yxu!G{HawjKxKkYD4q#BfT{<-o z9Q#LXFO(XvYCK@a0M=Uy!RhhRDq*&sYxzhgo`wArpj(+)9qtvxh&EaUL-3dcX#0R1 zswHb7{dVglP#&qS?#DX~8r@%-CB!$ZUkrl{gb3LBphH;HPbygI zeQK#h67@^dpryaZicOya!>fW^k~@cFs`o)v`y5}?H~V5zu~?&2Ew4Ir3IA|tid?t0Qn^bTkHQYNt7z-9PY=c|GL z%#>b0pK$Qz`T*X;!F$}nRU1eXp~GC*K*~ZVIBc&wETN&a4c+2A{Tcz!-#B=m3G6xe z9Xf_aaJE&6c56L;Xe70Vq57h1DaASe*{>5S(X??#@Rzn9yBmWLhSyyeL&BEu{}WX)TU5aRy1?Q zrltUeX&5Q!a~%p}`)1%W4fR?xsXtlvC#Zuu3P$vV;Zw~)jw~#+)>>R+TWt^wR=8X9 zw%X62R6;aq)@ooeTbd)hO$x~p))PhRVXqd_M&V<;wFM;YVugja1nGBh>D#xI4#Dar zmFti$*Kr1&(hB6-QHES!>hSftT$V5NCW;qF_@Sm?l&w^jRnzx*Sr2SGR@kr4C8Uz$xuO!F0T}BaDiV z=zLRSm~ZXvqyjjHPN8Y-0os;AEk_MdJf^)TuNk<76A0^J@p<5aLSvY}Ds_;ag@HR^ z?{`dRY2$)=ca(~R88q8+T+g0LWXMF5xQv!g(kNjWlkuHSAmb9I&Nn)R2DNsU1`3-Q z^v%uyeV3{8tpQqwI)?IX26ei00WP5i8l#)P*4a`w2jR_Kq-5)NF>aOp*Dg|PxFi9F z&@1~1o%*{NR@vb%b@Se?E^ZdON%=6`rhZ!94Kn}aCOp>-#$A4~v=g$N(m5))drzo$ zZ+8c*7|Wb}rn}S`)nHiMzXvE5%}@*B-%ixt9#T)#m~%X%b8JAcnFOXcdd6C8DEv>| zfR>Xwhr3IANpsLsT!3A@K!AZ%0Kc;a5chgaZxCY~7vr3sKbDDnp*M(pmt!mSktU(} z8s9#^cMe5a&g*n{%kZH=KJLSweWi5kx>z?KF6k?EMH^%3%s?BBU(^d&7t4GIe~AzM z3|Xw%u8X(#lLn(NxlWgK($8`C{$Scqxu4$cFO5Q%xjG#OfI1hLnJ()jfE9YdIDXpz zDHq-2*!BYf`v)`7boe*nNZZY=1HnL*Yp|ipQ%^z;+;pRD#hXt`%}^}Q@gD>^QIG?J z7|RcOVK6;@3d))=NUDb#aqIVnId- zH9jpLJQx^(K6>yOYofuJ)Qf?RJ%gp$-e>|BV`45)gB$3n`1SbJT&X!3iqfCM@vU5G z3R+r&Ee{_t3`IZr);Scl5QK*wi!(85^P)NqTA+9RYo=-nEo==fA8UsD6$x}$`9 zqWq3feq0{q))+Me0S9t~++tvAcdW>lI>WUscX1vUNG;L#jHz~a@PIDPImfd$$wxrv z7*o7+B-rOP_oe{{$4Z`(VjWS1QYXRcUDHkLsiUA6wWdkygL*OEH631~p<_ngHF0*4 z)EEgh*$CNyIl&@(~n8&5kX|#Z0u`(WPJeQ#?M|8qsyzd!UU}NKBV^ABI zccB=zK=mQ;fmM4bfKAP>jfbJd7I#f+PJpWIFl%~LFLn#lbPLlI-;WvORiwNY2kVi2(-Nv@S%6)yhI z_brC|^aW2Z&iA#2z;9b9{2$qjV2^inFgS`vN06iLBxwSI#qpdOFbq0B1tj4a52r}O zyx`nCWMpZPwsnSd!^?7moz@eXYI%p**2K|mKW$%j zC6j@la$5QZs9nc$ZMQiTBTiVQM(em?x!bcN;J2Re}(>+$yUQ&u*1j z@tB2@^VCpf3e;|u{XI{56JiaRrYv0``oOK{va!_`z*xSgj_p38_l%`Mc5^Xw2R<+nBzF@0@V+;|lJxBU-ldYL_#`l4 zVNuq9i4=)fyaR2ihK4m16Pjdvu@ok9@Rx3tqXg4d`P&t+@n;zJf;vK}#)W2BtE{_B zdJAqbK!K^+UE<5SO$mXEO*`U@SEP82+9)10Xfk>t<86PWbn5JoUQN z+4_yUsp`K0iwtK>rn;h=iV(P%>KkUNqh^H;n@lzLO=-RGx32wPWq@h?ZCfF=LIH{F zU{R$+Q^RRy`}9g_F-ia=L?22|q{mStDs7l80WVr5H6ppxLNys5t->CzfQ9C*mg-su zCb|XFvDH#vG>p`n0z0d)-8Y!o@@b6KPwA`k9sKO_5qS-B}~8M>DzF)5=3uTL){H zuW;nj@{qr-lV+nW+(0|HfvBuuwk`PndZ{+ar3Tt)Hc;=xe-EMS8>ATP_wEL&{uT`B ze=!^A2i-t~!o@(}a|2y6D|6mtpzyb)t#C$U>wD0~kegKq9xow>3$@y5Mt6Bf8U!lwlXD=^8>I#$liH~sW1|Jq`3l%6bd%K0Ix@*EkS1-C zUV;XMib$SK(1PizZYx6NVylr!ESU1m`s7ih7EIr6hPLTtgZ3|#hyHVmG)Z{NfL>P~ z`p#DAd9;_?>L8)&DD1@#--D(bQmK(XG8-u`i3XE4+_12gTsz@ZLdGK1@zGyJKkaJw zP#nEoiiMq;*6=5g-|#-Kn}v^MU)nA?1cZ|51|#{K|ADlV{H0UH;}2Y>ueih^ZAT%= zY$2fk4(N>RFzF-Hnpby7V^9juY4RZqmlN@rov>_tLT3_(r+)||{+0}7IjQF~C)i9B zm&{h0zS=1{&;SlQrNjE-eY+UU^EBR27N6sF+AY0mElqZbobCADZkTvZPNq#zAV1r1 zMlYxoPyPrheknJEA&2pG^!`|SL$EG(XY8{VW=*e|8K2V`FUGU>N`27cWIU#hnt?0r zgFZ+zVV8YUbL&o5mM8IweNrm=gs}{wuk1v2IIpwZnaq|s76yqDZukjU-a##oi{amB zJ2&ZyPoQJJ=*~PlU9OLQGBdxRGryROEA5s;JyAB?4V3r)jWSp-lfDLZ7Ge-47ANtg z-Ew23rm(3$*UDTlUA!S$Sq$mtm~M?eW4e(z(2hwJf2K|SgB;60lf02NImN~CC-K(L zrPinpD>jf9dnE>GXAY7b^$$w#2%ac^|3b<@t;?pw!@q=)Z*mH)JNWRIk{WE7Yh}QE zQ@bUPqYuH(ZP+0g4G)65V@)j$TIml1cDU0XqzSVbXgxef=piY?@$DgLkPPEQe$si$ zVqjAO^1$5Mc8pE(0_zSFqfSt&{+ZyVaS_~2v5<*+EvuNrpX zLZ3(>s|57bNQ?hRd?ABB9Qh657HJ>S$&Wl5=@<5yF*}lRU@9GDs!hm0EbNc@r(;ns@96t{?X}lSa|s4f;8C^VYiDg z505E_@S}@TlqbTQgs^Togil_Q1|le#zO8ZXlBCu)Mwp?-mh+0LBkr>Fo;T_NT%evs zl~K=H_<4~^-8I#o-8Gokvv8MiqZsC!P7LR)XB&UiO>ThkdZzp&{cbIBx48e$QdeOT z)n9Asdej9uSQ#aF#m~~)sD!IO`I@A{nQ}{PP!St96UJJTwA!nB?iL6K}zdf0d%q7B0_=zd{SYk(XhB(K5DK zPnW^|vWa~ko&9OX{xoMl@&>R!!Py&NT!rH|q<5_-%`J#&_o1Yjdab^CAt+7ni~S7g zk9k3cBwo;lTX4iHK8=m22HpmtYNW9>?tVI3dn#iKPYzphDzcnu^ohQ-UBPC`k#5bZ_l^fAR2hxaclU7bdQw)o?mJH{N=#T!=BiaDtjYze7(oq4~xLLyg{vXv$-2ZRs zD4JTn8Z+ObYD_9m4T@oEJnf>!qX$y`R=fi=!2WwPf+zkX{f*X^FYL=lsj#cc6P99_ zuy48u+wPH+8Oen;z>LDuUbVW1KrwY*w;oC1_?JggGWx1~fmi)S1^&V)@L-o_k7Ag> z2Y7}1U-hz%KOaj!32-<6f*@C{Tjf&zoK|+XdX;d~yVY=)Zq=Z}6{aieR>NGnRRit- zj`EU2;Jpko##??HMb#>|2EP~SP5PvWT80|j(8W0v z!<F0yr_>T&)?kJgpUH~%JPa`v?=lSe!6G}y zo(3FmL9+d1FTpy1%j|rina`$%)?zb1J^}coHCTdaIRJlJNj@kHz!^bu2L8CR%=di) z@%hT~D&ZMC-Cri#KCp9I&vD0J9wNZ1Fr7rbZ07ly&htgbA*-Axz+G}+nuX@oq76KL zB}i7$>{?{X8{;?_BsV0i=&Z_NX7#zwYMbMks&W$no>ZgqT?+;lTR6X{5CgxiAq2*! zS?A3BzR>xda>&&P@D%0eXUO@EbKM-qxO$#(8?>Z`4|4d2%P%796X|YU=axvhFOt$t zUFRWPk|)w}`|9#M1b@kJEZC4`r~?@|B1-NeMB(UoISK#frB*ghosJjMh&JFov}7KV zG91^U5a;fLw+9CVyjJBxuOmuPW@{2@Z# z8El9;t*+i8zEM}cfUG=YQ$1)Ww56<@_2f^iaTzXc0Bmw*%I#5V25Wrzjf5cCM{9iJ zaOe8+MiiI9W@IT1fMsk38x9*_Q5pR7VFUSVYZv!YN*c;JsJFS4DtakhaFs?-N*7j& z#gNl+X=6DPY3v6!mLFNiyR#peB|nR%nAum=*^kGyn#f1HNxZ9jAzKy&>t=UBSG15jBL@>yJ8@P`C*PdG z&J=l|9Mlphzc8z4q{P=-$^#KFAWgNOAqN709Ew8U3Ha4k@)UGEgPn@HZ8#Mb1B+d} zxBVI4yeq>Ilh$%J`iDVbiQrai8LmrZu97Ze-=q$(L^j~Bj zH*s_~xhvd~1Sy?&4w7_} zb;Vn|$s15t&URjRFh-}^I6#KO%!j+nbK&lWZmKywAa_h{Hs07vevGco>dvhm@^WFG z0s2u-$eqogmK43b(Mx;DD}_}$(l1rde3P?QdK*|b>Mc(YJ~R-d=>#8ef@*yX1ReUw zlZ2xNf?7JkVNQ_Nml2R*i2ED($vOepf-W4>JDLW&wdabT=qq2g-gUS77yZEMe-j~` zR!`Tt-o^d<%U__o%<2|H&MiD-05lrFo)$}{=ouB6q8mihVp$m|KeR^Gaf{{VH@=uv}O;YOrlw?ub0sb40a??qTp` zde=d6H565c1@ZDh9)g%H5?vf5&$9M&75*k3|CHPt4TdLc;2Co5z+4^Ou>G)Quxvy9 zSOI>9oZfX<*j^kAJx&jNI~Q((RvscxwN7_0kY~W&V$_264acy8DnI)Ak2I7`Z{|BzmYGufTsI$ zKFoT=y3C#J3!s!9b@bZOwIa2}5Eq6v)Z>!|_$`~<3V(S^Y=V2)-uxRXaGfl?H)k4UjOvCkIO|H81Ge<%Z38su-n#!gzhH#)= zDr=2SjhEjPz95oi;I}3~#2w(_cZvMi51RrX!a{Yx)AEbLC5rNEs|W6RhBYPu1-)6; z0KVA(&nytWe(iLM-#LXLNu$VrMqVUT!eeHDB*~MYaJ3#A(6-mf0sG%Nk2X53)_Gi> zB!396N7Hh?np|cx?LS3c3lHWJm|rKIOJgP!j+_b-HmJvx?J`xq1~1rBmIc!wqX$Q= zAU^>0--I?4$AxxOpDuS7gfXOuEVsc?8vbd9JlZ;|o=d}X5|5ZEH-o1vfeIQPzJ^n` zuX9v63(nZW@N`x^+G$w~IWzI}XXQ=spa<1y$aA2^2JVh}I{jL%|L4!iBZN;lb{1gw zaBQXr>@2wew(>HbhkAa3o9UJ3fd-h-M-0AvUY-me;~@q6HPGpQ1MOHXUlC-Sf**+tC228Ag(<}jz@u+tfQYd2gLEu zWM@0Rnj^1K~o9ZNh^=vbPh@c1!Rbn&zH}FAVt^XFh z21{$fJMkqM?%u6q;x%cmi)3h$5-Yfgn6XH%;fHpD^~>3;Z!wkjKyb8mf$aPoqw8)x z1+k`aI|n+K9+KXa>j&`-00T~ILT0}ypSGTL4;`|Ph`u+6PLH+D>UI`;t%PC3Sr$4L zL(YACd8K>_3H51ESbFL-kEkDU(rWO<10FyFR>L|(2*>u)vG9uI8VCvvHhGPF7}a7h zJZUWi1#D2SfuQKElK|FpP#8qe+!(k{4iHd##;{#qoymW9qrusZX79+$y&MhSk>B=0 zgX)*-*P&lgzYZX3l<8Lr;wyI?==AH3&2px;3uVClcLf}^x5xk-qX(fj);Fyn&#dOFEhen3&pw3+f9VRc zA#|E6{?_sC!P z2s81yPb(NuT*_&9%vbIKHJR|y1Il&X+#vl#rlse2GT;WmsbSN{Yx^9~m(2~h`;HX{ zeO$IP95d48ACD5smJ~=oNDNP=6^j9?>i({!+XAz{qR$Vlkp_SntIXaxHaOt^Ux29R`|TF;Sw3d*#;$6e!GsAK#4!cIcv?38{_hR|VQ z@g6>Q8agu%bY#FnKJE&1+L1>iT|-Q7X1@nPO14o9S)1Xa9{IHF*JojT{BA=s!HRJ_ zJSztZc_#L*{b~j>HefM{HuopVa>6_ex-f%ZJF|-)^%9>-wJy{meWe(hZ9}2oa z{G03-x6&!qS+F>K-PjTPw>(im_c-|L2LS$qf-Ug|Fp;xj*R%~q>~<9YBYz@TgBrU; z>M7jnksO_9`eJb;0f~ba!^*rjT%67^tjkB?%Zj4k#MZv_4IkjKDv9o2>`Q7)w@+f| z_6g(VvSOJ?Gz+r@IYvH~pA&?jCAX9;kG51Cxq`CHOXx%-;Cq{CK8lLkH>S1UlBCxOa+KKHn|F5>yJ@~-J^#D!p6V?Q*F z*qTIjWQV#S6hsfa7YtNQ@j69m1b3=HgH+?why(=&n}(xRB|WOF=YlzEw_}W|{Dsh4 zjq!{cmQeg`B_&zdN_Zy1Cl-D1`ASL#$?RUDgjnBlkBvr^l|*wR@i`t-S*Zbi4e)SZ zVgC%DuB=paTR4SAMJ2kSmNPbQbWZK`+I3xb*6K5L-*S}tD=={NAmaxCN=%X|et*&9 z*N4P!Z9@S6stZn@@6-bL=Q0BLPZq$jR8-E)C4w~x@g=KLLX1herxcpXTC0DLlC6Qt z`=%&~%`!)c6@F_wFU}|ds=D~gATUc!yfRoZzbf6F+0BX@S5a!0873UH8$*}`JJwWD z{vqG}24-2pZhRqF`59Iv;a7%VOTvz+(;V1`#V;qr5jP^B3>O-&?n zKDE|bCm#qG?8#Hp1Mx4RN;cBCHLs=|7ADfdaI-L|syxFnI85;q;H@(v27V*lkn?f4 z5-h;`R8&CtT9J!@j`&C=T7Z*Il=7MC2Fh2fD-i=pRWPr8rH8S@D*|QT3~`pH6g>h3FF&KCj{(&Tcb6|#Fcd{jZ>-!LM$uj ze7vGU6tG@#0Dcs&G>5L1biC*<0ryT&R>8Y>AQF92a;Blbt$onxie`B03MI(VEm8Rm z3Eddqq7>lEGhRwj_95~SwOSByJZ)7iCC=Mg*u*Wc&eTy7g;IjmH&7esWfkI9b(L1` zgs1SUb(L&$D>fTns|zL0CCv0zOg`@og@)OlZ-N6lDS>!OJtZRgPe_|D!*eLPMWb>G zMlZJABMBlTluj(pTWtFqXWNuW;UPX#Pf0f(Y@wos*$N#InGmP$a^1vj>MM2N9xPGF zSyPM(HDT?tn<-A=tM!#Mvqm4`=mub(J)Sk%#Wh;h;J;|}7|@LLJA|4V2dbL$ z9&uG0HLI|yY`9tncWqdL~hER2(w?BpNX1n&W^>9)Pr3R{R(oY+R*TMdslpwsWMTOPl{VepZ8Kq;#mF5p0 zS2!lewV&10#Az*+9SHnEdNGSZ4PHANv{HUW)+d{~)y~YeN+KG@te~A-$NBze!{jasFu>Mdt+q7327$cbq7G{G_akW>@xC?a? zPw4>KEGtKwpE@Wl+zC(N#vPSbW^LZZ3py&z&?b-CyiK&psCXkYqmxp{lOm4KJ1Ij1 z^kh?3C;NBN>*T~PN-nZ~I z6kgI@X>Qj3CjP#=(iq+LsQquum*aa>*q7|+!>`?y1l+Au_BNV=iXLYB23P5+9Q3Gf zPbC@oH)B(B5BfR=_JT$VeZy_Ix3_M?OTCq1WKC%17WG5>DeX}@yys(|BtpB++PU|b{Vo#31KDAVH*G;fIv!8 z+wqYnb&YR6spKH*NDmqh26vX2t=K}>cqG0sSZV1_cna4UqBJop`~sdjL}`HLcvN^6 zSGZD6g%yU1J~Bs1F$M*dEX+32@pg{#hail^D~9PKjoZT%KV;qHuA~2OXwg3~d$pCW z<0kG^H%fTIY`D_StmKzi9HF#CUwKsWAXjqLi2tJG;}J^zAj7F2Dq5Hg#G8YC>~QvHGwXTxEjslb7wkXf?!UZrU`h9P4b# zbOC{Ov`aGhfpI) zno`GXzomHfG$jo!^C;9}CRF0|3Jb-$fp@1VVXjS^CYxi|bmh1gDrnA{wmr}3P20ui zl#jivAGzA{Cf+<7Ch(t`yc&{>cAo@DwqnOk9f zlj!<`C1>og;;{wK#VES ztOQZ*3X~fU7p~4yXl-V1@!Uf!Z!oYNB?mEd0hIVBFd$%7sNRLxu2=;$nXA=XX9A+E%$MpqYAjI}AheJJ z`sjcKT<>bjK)kuxYzw0OGG!)0>$&6)UxlnS3}@-5lg@QCU#^5A^fAZHdmV7QxFQ1# zILbBFap!eKM(8_^PF(@$;~f2@2@NWG_*R5L=w=R>oy*92Gux%*I&naQbRK`+kleNlZ(;`~!7Uo5?X!y++(S}12Y^fEf;&A14P*>}=U>$|w z5Ho>+B++>6Iwh^lMKq3T=GePV*@jTZ7VP|1f$j`2^jpduFKd4yfpN9$6n=lB>r8$a zzP%A9A9*b_tCDRPZFZZ}f_1H9H&wXpfKkyAKpPwIkxZ}tj>nsnlL+;1!MawO%oh20 z*P8I2a@!ltWg6j*4v00V3iKi8*|^Z5%totV4d`P_a_Abv0#J*a&IO=1Td;2eKD9%M zN81=SWWNF1O2=-&**BnXy0Am}-n!4-QoC~18s>$7LoM))Ts0CM_GqdvxTz-Z{4b{3 zm!}3AP1T0T7iQasAMaH5!gs~??t<|nl@z{|vRhHS(47|e*hDz4+<6al*F0zB9_3HL z`b0}NcbDt~cbgWg6})*L*v8UQbGLC>TEb(#P^!aHy<&A+hpLKmK2b8#X*CKMHL7r2 zY94%Ds;G>YZaXkNo@j|b`9#@(;4dBWzqVgdD{tY(h8m$ia(i^YGFYgG(?3bzHgn*+o`Ljr(#8j2NPK_;_m=~Fa1dq$=Q;2U1!@oc zO=?NsuG7BI`84CgU&`fXc6lk+5&fkyQ4oBW9#=Bp3&PzG>l#1NiaL&K9QGBsG=jq5 z>zrl69(<+53Uw(AE*X{yd-JdoCUm5*cAjDM3E`}-l>}iZg$<@K?M>h(@R)Bw(pD^j z9x~sU-mrDlIHHUYgqf6hnyHM*CdDkrl)J(!6t=V+*!1I|*cJ-gSPpF7DNyWl3j4Gi z*xqlHp27tRJ4<1jVw3+>G5pQ9$|QNo>k{1ag#Y0#-zoEjN0ikAQ;GMCYB~ma1H8Gl;oj0SLIUxw6lzW1*>JL;ZMh6(5y zPCvn1QfX^rpoW}-f%qbhe6c(v)pG+!t}PEq_1wdeyURoNzM!O{6CC*sLu%Et6drwp zmzTAtB_FcdD!-;RgCsX{X$Sb=r4MNytFiRj*me;X=V#-^@JD-JvWsia=lJ2G;v)z? zIQqV}!5wy4Q7wk%IRn?e46Av8ZRk6Ak#HkL8`1P*?Yj}{xN%wWwxHNHu*sx03N(P9 z5}g#?L5)Vx&tnO zZS=CryLm^6@I)7RSBV$k%kpK>9s5TKg|oFQ?rH;tAbk6-^4R*8yUOSfr6p`b8d)vS zqv9?6{2xk=C%Tuasr7{YWz!Y?sf<8xwPB+=14lkOiT?}s?yP6s= z&sm&vUzy~I?#6v^!5?MQ4gFi`;fe0R-%5Sh*Ie|E?s8LkO&=(+p6E&*z!r08*>raw zD1AK94g3c}EV*nt;yQGe*$sz3RMaR#eeyW%zzrWME%Drk%5>As$zE;EQ;(MLn@>I9 zo78mbK`3Xy#dWH@Va~CP)svR^!6T(!sOR$?@S3ut{bOaQ0C5lW>@>`h^Qy|mpFv9= zs%Nc}NSVgT#!38(pe72>n)H8N_wOX!3#m=eq_#9}f(T|Gt=~TzER;SpFa}+h%&yezATege7 z%vYTQABEPb*6CE=P%1oER8^$mcZ%x!aI8uoXR1|Y8ZT0r5#%{*`SjM z?bve1e1(a;EAEk%)S8||>|IGsF^kw4zf?($ zM_oON*pY}Bgez56|HB^p$jWM%adxH&<#?sCT3J9*?bxj5jK8xgIR5rms|nUpSCg{J zfF`$NlYV}A;$7XfrFfxLt$|7z%V0x}A$~LPL#sL-K99a4SZ!>q44as>cx5;ds2;Jd zaTnq5nraSu*DS(&x(I7<|0-&Cw1#VSu8L|N3^?vqQQsAWPu)u2ZYmvxsB6);EO_zh z5Emx+R*1S&xZ=iRw~2>eHMQ7!$6W)`6QRG&8hoN_a0mN@sR`%~*I;m%(=T{hn7RO2 z+v6GjFn4Yit}3Q+j-z+D`ZPGSy<0PLz#vzkBQ;V@_p+w9cdIZ((Q2|e8XMsa(P|vZ zYHzGC+PX@E_IOMuH4w+eR5%>j8uZp^HPCep`b#EaI^GhahNATLEGQquXvzn!uNJE! zYmTebCvi$mFlPZ61)hJ1;xYM^ZcdGYZpo(Mqp@llK3`K+J+Y#(HHop(?gklI;n(8S zNKb@c#i?!4f^rCZ#jDLw4$~^wz|vSR;B72*nSj=|Cu7efydqHzFjkMl1}6qNP9>@@ z3)c7D%`rJyZHYcIi*iCY$NNiD)B&F83R6IZBaBWvN^YcUkGl<$L(%)(GtE<7>V%_j zs@g|DKe}TMprg3^mc6@DvWH4K>9y_^*#U)P|<7VF#_I7}s^{btq%#-x5|ChFa43 zX_HY!xp{@D!*fOz6c*&UbtY7!Fxy|WhQJE}#dXvy&&yEX)lu`%PEiLD4`0^1~&t>@tQtguNv(Ot=XmGngOlBO)?qer#5J z7o*`J+PAqn1r&FJzbg;iI~y9tlla|iF!x=Pxxd$)d6PNwCUYk8fg}65V#^v70sA_% zbQedGMC!;JE!2)Eq!Vrbs`4Jt$Qp3C`$#bf#r+qq{;i-xXvnx~ouQE{v1vT|wLHx$ zwN{hBObuJBndWiDlXyyNXzicsq_vjD{h9%tSU~u;sc=BB(}-cXb89s$)b*Giw_%@7 zG&Fj4qLow&ja?N8jc#pWgt4d-Yr0-!^x79~=5;bwa^H3^Y}~++Ys*8Xw5K(^pgp*5 zKQpq{>;9le#hy<1Xk#@9!C(3TrSG@{DJ0CchZgP<79^2|#XB8<_s?br8hPWK&T0(# zXdBvHhNSSVr^evF!yR46g(~*#q{hM5#Afs~)M)K&hm4CmRd^-^b@_59wVJUmbM1UO zQ-`6>CWp-~IUpB^$a9Acr?u z7ZZg{*JcO+1e<~P^;FxH`5qNVZGjENb#NgfyO+As8&)xZ8Czqq+;uT_prcNI^($|9 zz)#2g;fCqSrhpNHG zN%LRK6rW>xn7SW*-kDtu`e_){k2|E;L}c58yX30bB#+(<@*uhUZmigaEg8%BSb?D; zX)`RJF1UN1TG6{fd;!^5lQgk;XnjsXD+__E$aZwCFJMnOCqEW0t<{A8;s-6Z6~Ove zPJZGb(uC$K5F@R0zr2ZO3|9vV4Tz}p{=!wmmUNG*5(}#^TRlhg2=%@ov?0I@+^GPT zdFpjx@BAz%P+P*w*N~Bg`a&8x_R`P>fL>kL8%8#pIvHMTB9wl^n>cxn=Gd+y8P@YL zja;1o9^V-OPTw+8T@Pc$!7X$%E&jHteG~VF)N8{DLLKT|fxBUrOixz8F z76l(q0Bq&1Y=!d11a+e|rK?M0%wAT9&#eG+xctEfI`8YeQo6F|4B;qGVJ-Y5w5c99SyND|H>D9q&T*TmX;Hl5dH_Us{W% zKC7zH24j2d|3v)uv+8`)Ii{nanX%j3Lo{XG-dQM#bbFL47SDMOI=|yIrh;sSJp}>- z!|%b@o>M!N+4*r4v~RTY8#zmT-wO_PfvK`;8^o?)j5uDJqaq1CEI%afz+eX?`@6i5 zpcobsf4PLj@R#+FFu-`g?|)hS-AjnX$JX)g8(&+hs{aFBa2!^r3bpZ!O=@yk-v+Z@ zr<&Bl*~?(yFnY%=^V?~!1jzM!h>to*220n32~QoYPKi3mFv`6!j7`(0@kY~p6HgYhw{EGn=X8V z`UpMKjWq|I-h%aDYO)|l;ajRKz#_aeQk&G%4f8*Ufgj#hU-N?JYsw4Q7DH$Z+$}E# zD2BP`mP-uu-mJ%f0mc-<+cv}GF}OQk`7#`2pSML-{wKBW^DSy8*sc|}t7U#=V(2ES zL_+s+x)h3GO4MXHXRZ5rtLprWi~(k}c-ar2Idb1qUlZWj-|_?;`yCaqt5HDLM{_8K z3D~K-b4=%aG-vmASQ&$>EB{}6R~{Z!vE}K4kfo~yLL_V^H-I4lgd`9Gf|$r6M0kWi zNJt3SNjmAiB;BDGB8oIPqTMVS*-CI3!37`g53~pT6kNb@Mg^C7i1P4>%ZH-~sPo>8 z51(^R)!n*p(#AL6%=gVVlRr*w_c^!f)bE@+x2pQqsk;tZqmGK{ENPBXrBg2|KQbj^ zo!cGGW6{fqpLnOEGJZU0?L**DX}t__WX-S8gWdF!b*|-JLlM7P4F+ml%lwC|Z$z#> z1U(22z5g#NbOk$h*jiwD!BCFSs^}b^e>tf%@J7WFZ zLQ>1)4j6Zrat(Wx8+v!_nM+(oXh_TT&SMy&s>czEBviSP&)%@6_UlEob3bzcgnYL1 zoRuHql6@L{VKjcsU}Z;=`?I@GTYIZVtc=7OGD_7tVd&MtXedAO)@ke8mqDfyEVE0Q zp_GQsD#rn6$46C;WJTXvO=qmAnm`kB1WFxefilR^@)&PSJFgqkAlF4hwx74A^d@WL z8}fI{xgl2@4H+8+xr{L6Ee1m>R^$JEDec#`qcl3}*Ip>dICOrXyyL82JB3|U6*{pi z+ial@h!abD(yp0RY4$#YS^LMN`O<1;*M4iw%RT~ri!Tl;X=hc1z`RVyBtP;!q073% zA`xoRrPIR%{!B4_$39}H?3P#`DNUr>+{+-RM6AaX>BHoQauKm^O``fD$;(Of97&ol ze&s)%OjAh0d_GCGy?!sagfKUm&$3eJ=OlB!c){j~&KfMFncE75f*emP{-Bk93aORX zP&%26Rf;>R--E>&4m!@T(SBl_)i*NJM%xoenW%@Q^rh+ujE(3^FQqP-A2Vj$d?l^xC>+0*^#7?v(4XR?BRbWYUz=`LuVu{X41bI}ADr5`|*IFZEL7m;o*lBH34Gr${TxV5RIfJEr{{A^UO7v zP9?n{-5B7nZYcj!Z+y}M_U&N0gTQ~`6IVdLNLV1&oi5-9vOshaDTCghnrE)yoeVmO z6p0GdJPl{{3i4QKCcTT~Ddnd~P~=sje49Z`t!24HpGvJV*OHe7%~%>;%fITiRI&Y8 z^gdXNDjNcQxI!u4AOPiS@6vVYfEWWtii1RohSHf9%R07Z7%d{3Ko^fSwPz zy({93>bQ*PJGKhZNjiBbM>db9H*|-r=BM+!_AFGY&lS~+M`7&AqsHplJq6To^5~ld zRLcr)5CbFge2c@!g5#4p72;WVe<8I}19sZ`u2%NPLK-G^Mee@wV4o!w;>kGd?=;t_ zsSur+6w!6$CPnx_5eNr_FuQ;sR557+y@%W_#BAAmF&h=(ffIG%Na;jsgM|D_q2a56 z^{^s$7(T#{g3$2v?fa8#>^PiY(WPE!P+jr*$hDK`PZsj3QjPnXXh8DWx@+jomgC!} z(1~e=9SQ||xsRx*-Z+Iu2>GK@$gC336t3h{BX-oBWApEU@ zAt-qQ?a7f+*w zWa2`$>!##*$J?&RuaMli{ zHXVGGAL%)hX7?lyF65oQv*pq9f9D3h54GuRd6dhDPJgeE(-vwhbE&pGY7qPN+Ok!1 z>CNOwd}Zr0Z5W|mji)S^5y~ElQTCt9sJ^O%MVSTx@nY!p^C+>9Z{lm{oxwHy%BW%N zgo?|Es=r*Q$57*h%96XKtR#(HHJ{!{Y?WKqCJ$hb&!@F%)=H4iC^eLjRH;o(t!(N7 znx;;P6QV^siPG%U7TN-@jD51Gi&H11f!TVsv`@^`DWQ_JSJ0x^Ig>$Yg1W&L2v90N za;}12><+)=q6%G^GbtL7%DAgMXa^PJn0fU-RqIa*gHmct%c-G{CXl8|B^cc(Vj3UX zX4>f|sR2cKLwcp&b#!?23mic3sG?J)J`KRPtY-jj{X=QH=UPC~csdEF_|| zJGqfsvkcw1!%0mdD{Q34qvkTd2Xu^cnIni6DwR>XW2;TfWyUqp*T{#Jrnw9XK=(ev zCOGNjPJa$lq(E){bJ&wkaNyMQu|_$;M#?at{0bBZedC*FeKgI*^ zi#A%^oh*+J-kC}co;x0RTt-yAEG~FL8wh|G%V}Q=Wl5`Ok)@p#uc8%wm0)WqYZH5X z6)owz3yXwY^r(oaWD~ozik=`(Dh^Y#hFX(0ffNKd%KEQ{G7qw{)wE(z2W1Me-EixX zlw2mQPVCW91uq0?u7!NiVFm6rP{A2gI*YxrhK~E&Yl$peOP5;6B||l2Qx)Gl%kmB+ z+X}CQex|L14U*SKBN6W*lajVbMUBn-I4QkL>#vHf`z+EPay0f7nDuPw?bNjXYOu|n z@!Z@Xw+!CEh&rod@;d!FVUSbf<<51KSuBvR;ZB-w`);-73xc1+{mqg!VvmOvnF3xd1K>tE4e-U1J-F3ax2nBcY^e{FSd5Df9YW|l# zyJ#-yTP+s$at#Z6%pQFeqVt%}_d z0%=b&+04B(EA@;5yfz3u&u-ZZ%V}R#^HJ4sC5>jaZbiHU_oq2~uG_kH>#bYC#m`i; z;%gGKEuTcS;FJ-Q$f_sk7z;_R5ih3qtcluv5+%w;Jw-i4QY5d4Cpq|O>L5jmhEImS2E9%}7PxAHW=tZ(kk=z_la{NAeCwWql{B1M@^J=(jbOr%F^ z=GO1q4-W8tbn6%Et;aiJTK|^P`ZuFBJsQ>e{m(=9`CifVLOjXaUZ6YRpyag&sMy|; zxH!sNqKmyhLbt#XX_|0`5LVsbXnYL#-l+5cK=V>d7Mt84{{Wo}JHVmnt5h$j)p5WZ zVsI!~EWBV!w8E3Pr0NCqMOtEU>Iyr4Q8=gzuZk!9&Wp4L&N#1+^HUSeRII)^0>DuiRDrZUy0~}zs>(1HO?LE94S{C9vpS;+Joc$#r(k$ z{0Y+O%!ZdU1NJ6|#5W-NB&U6aLuw4T8|*C(x8L5}yi)Re?QUPA$J^p)ker@2$>(YG zx4{7vlFKJGI952CJ*~j8yBj3j4Ii-k9Sx(U3U{+>nL~mMTPvU((AnNB`BwV;juxNf zciR0@t9OZ~AyDst3rB;i-fypKc1WIpzct|Zjgn^1p5v369Bzjfij!8@y)H+?C=m73 z+3R43q|fiFm%I*NtHYcGetW`uc#+4|%^D zB)3f8^f_IPeyQFGXgJ(WE_c%?Y?t5V4!|`Q;&lK_ z9=Fu&XtLLX5)RN0I4zE#-|1=aAy5Ig4{C*k_}EU!jpuau0B0|t+~)Bv^GR(E0MzaA zgF-%6lUpd~1W-YFzZ0-_J3+$j=U8wI{7_{h0;QtHP0;3QZk7Vgepd?s*Bo4ln1My1 z-Ui2Vw9RP6d8+;=tRIYH{{LR<3nOfKquBO;-3Kx|@&P?se9q$=TQfE>!PXEJBXDW$ znjhx}>gydoANct4fD5{uak)X#)9jP#0{E@=B;n>ju3|3?h#m-tZB7iP^`0g$ zse@a`-e7O_V|9i|+!n+j*X*!ke1@AKSVK`xyVnhlDjX9YD;@}`N`&-{mS)1o6%Owx zen-6rl!V|3QL&!;fl+zCqu%NEG<%v{_4v&4+nd~q_h2JhJ${FKgx>|MI(QaijZ&lC z)g18Zk@f%aLQqF>qjS85c7m7gf!%8P?A7Ls@;)5>45)=cjJ8v4V+uTZl~E965T(Od zdrrz=#<%$QuNBkfm4;D|H=>PtF0W3k7%7)j%@N1BKIsW5mpZH?94{iw5 zIh>idZq0FK!M3;{D?CI;5N{-6KLi6!%dE)5hv{sKr7?2h75Z8C!4vZ*s>87!6Y+y+ z6qNi(Ehh8m#}bax%#__&4Xow_>e!m2G%ZJd7{18G315ygVIwKbQwzaMt%&_f5pYYE zWjEV>los~b1vm0Ch`f(oJW59dOR(%i@*~i0`5`1<0&$*}pX>?O_}ZrIOaw9nujb*^ zZ;;$$1u_l4TaQkahUol0iUfkSxvsvIt3dShrv|c@MI` z$OrN-c=huLAeWF#z6Qvj@w+Wo1L+4ZI?1);fK($nfZt8P?+Q__8m}Im1Y|do32;`H zT!`d;c;iV9A@_Q`nug>!OakP+@ZH8>vX+WztK0~?7-a&f+T@?71DOqbNaa~b_8@r# z$VS79Wb!_E(MbLRHVDaQkl3n`AcO;9K~+vi@->pPNFIPyRe2|pH;}xJ;SO=A!}8mpT!=#(;;@D|q#^m8AZH+mAr4@egBRw&g*a$o4pn>N+GlkgP*;3duhr=>rD=$UouL0=z0N4gy_=m&=hnj$|v6uaTTU z!aFRc6PE)>>`1Wd%J?dyj9Zaq+~+R;fqz88J1?eD79AS%0m_photB(~WGRvxkj#c$ zLP2=~Q2D_dfUHO2hAaqjHIgf^(^|0up=`Q!d0S z9uRQvpa>H9@}~$5_(Onv4#`O*=|PMQHZ4lvFRLO-v};k~AYSnxaR#q=kl2cmf(Hp) ztrbB67i2|{cpqa11_}Ovl1JCVRW6W?JzNcA;fa&HF{$3==K~X#{5Bl~+ZglTq5XTk z4>Ex|lp2?}RsMiw9RuEJ6E9!moi*_aG~Rb6-dK%y$;2C{@p>}*d(pZSYP{Yi-gu2S z(8Md!c*9J*2^w#-i8oQ>O^D^e^Hs$KGM-24S*YVO+r-mxS!m+vxZG&s>A1)yo{o#( z#M5zEZQ|*;giJggm(3=gj?4YAyzx3NkC}KnF3*~HIxYuIJPnu2US9&kxNWnNy750| zzb!G%;H=|yklryBqJ#9IiKl~f#>CS>`o_f5LHd)4r-4MeEoEzu(R72NMH)&Z#mv-T zB57u(h7-v!Gc}+{j+v=}Lki4H4IMJs%+%l^Gt5j4A5vy!Y528A z delta 63612 zcmcG%2Yk)f|3B`15_zv1Np2!R_8_tc5+g=p$6i%b2~u(GRTMQ^)!JMfN(rSlLAk10 zs{^$=wRTmjlMbyezt`+mRgi1hRQ|38mMKUdCqp4UEmyubRQ&Ot{V-|3Z?b=&Qm zCF1J~W!2tLscvr~W!XoG_3fLa4B@o>f*g-ZPTKDVw5nOHd-3p5#bb)bjUQ7SQ#4{w zOt+%pqlOI`F?i{$r8AaJU0S;&yyQpwXffPASBi+QHcm&U0Xl80h8|y%ROtA;2mAy z_3`_E$uYvyfRDC+9vop`V~w^q4`JG&QAV_`p+92(CK~n+?k#Mfr9TXbu-^}^iPkYr zYgpN)Rl=OXizggbf`s=ddSlfH`%fVO=r}_kVXBU*S`~tT$g(6f%6`0R5W30ouQ6&w z&C5*9zM)kG(Vi7i-M+S}pM6?bqS5NPWbR@5%yJK!KfC4 z$GgJufz6gsp`8=IrFyh|UbP^*P=i~hrLlx=nIlNIOtb2B?fq+16(&(C3v1+{rx~}g ztZdUNqP<%9cXpvxKVdIm>M0S4C6OiRCE>QRy`{BMe1)Tsnq=>vE-6vY9Q&wamM^AQG zqJWa94z)FDy81F3epXiygn>lRWIf9snsY{&L=sc9#HTgsohf61LQ_kEeNyfsVG&^M zS2AQYpTX1)sanCY_EB{b>}%>D6*k%XHy8ymaG^mia`@u>(MqH}v0=2d&$m(~h=$$v zjt$F#c9B0wctmwbON7)-_JBqm(I#I!`h=8WznZC_4Vom7&*BIq0XwGI|87*%I+~P^ z>fn?T^enpK7o7i3QAs?Qt!Ce)^NgJW?LwTLLQzQ~V3PVSCFW9$=F+|5t#5F8#T!8P z%HQCX8YL;V>O!STnqx9FWgdW8A$T$V-Or8!q3NuXsb*=J{*`%DI#ZO&B!2PXKl~=4 zM261R&zH(U_X9i4vlD-^7cR|eBZl=zfHb}WhNIDUYw3~&3*FE?O6lulxOb7k9r z%J|-IepzTxWfA~U!cjbj4N%Oa#VR0i`snl=zY8@sw1$cS46e0iB_eBt_ZE z2(Qj1U5K&8*CE|LL)N%kYr?Y|hulTgnEbeSE{MS%Yh{O1Gz z`NDsd9RXeZPR*(6QwgdZ{Le6w3--f5e&P3|)nH93bD$sYGDwcbyM9wu{NiQ5AemYz z+~!XUgyYgLrRw;T%YIfXH=k1x#SaJl>=%jyulP09qQjZ_Bkq3%yrkJ5uejppbbu37 zF$XxTSN)#xL7n_am?lMg3y!YG!3FK9Okq4aa$S4?5axrne&zX~)Y1H=-_QV5;)l!b z`9-2AKYZ?#VW5O z<}be_Uttcu;45ZYIt=)hOAl@5jH+UAi)iq&vAu^T*)T$nagNa4+Iwd!4DCJXHtgGK zs(8~wzxqN1zW&hfDPap?nG^wycWb@zE*u*qu*M>xQ&K0^!{ZaYb1uXeCoGkD1l$JS6Xg^zKO zEJg9vZ8}|s_^)*M+AkoJcbrA7A zAF#;t24CUnRmBjY1722DT!D&3=xb{e*A6kb_5~e2KqRhpybvl*^F?DBIsX@p`E*Ey zdxndzq8Th7r$&e>8X&SheRzbp3N7O~4I@QWSb|HV#1#LzI+caM1v>O~k>XLbok1=0 z^z1F9Kn~)lzoNu*=r||%cQg<@!U)dSODq&=Paf&olNTD84scA55ql!x3jQokY>&Pc z@r)K?YVcRY#!-a}bz)a=alH67x+2o>!p|mf?O-^L*CdEDA--d4inXhp1s`a=o2@eL zSyPM^M7*wnhhX=SNJHx(*n=b*?8&s3SBsx68a6gNKCguwROdOZ$9Q!ynr-?HJ z)JI}k^vM9PKF&BAU}+dQCOD2|h`$Qf=iJ!h6Io(AXdsPhE!UYm=jfg-UKP-DjETjN zHJ!4;tLlRB(j*d#jt}aJL4tLgJCh&liLHe_CMGL%Cfo4SIpRNP8|Puj*-Uuk2wVqC zeKAq6e&|lVWdpH~@VSZn%R2cF9XA??eggWC8>)IEFw}V_eP{SLNbe=^4UQXtUuh&R z5PWcKftZH>86Zm1YQiGiRtXQu69)%`$`CQ(wqW>yL0cFeou}sDevQS--g6|a3?9~4 zd{$^lXlDrpxTv`pAJB}^Ys~27h)P(4*M$@|Jf9(UmgxRECvglW&37gx^)c!7)R{4@w{dbHya6y)Y>*)|4VhF zlM3x$%ZCi@PC|Rm*2s>O9$uj@n#xaiay z7qx+E*3%?ucZ$=T^l2OD0%mYYpDhQttF1U0t>D0A6e#mJ?5>cNp}2DW^lhP-YCYht z6Kzcnn{;|r*NGHx(dhuwX`e~dJtmzRv==*|Yh2XJS?G>8+4^e2^Xb8RaTvXabRaXrUEHY^VE_~P)QpTsu@1vwua>( zpX@9S6uN83E)=QxDo~}q(i)9rtO>D`3Iq)v`70Wiz9~umK4gFv#L_F_EnUQJA^(!r zI;wDut_qBC$kcULi0n2WD=6+_Wnl@6WcZemYgVKosaPfOd=Q=H`^ zY$a(~ct{^;x96&Cw6wL4xKenVW>{XV?;K&jiDx_kBcKC762?iFpAbir;V>yZtuOQd z7fE)C|4VuSj=bGhoGg6L$j#An?@&BG^(1gUpwb@0j}4WU_oI@tL0w8e@lUIt#l^v8 zIJdu8*F4$@#FP4qX~=5PhR9@OFY%Fm6)X$}vrg|JD^|DBJ*;FD!MuSEjCcPk*1*$? zL|@||e;yG#+~$XIkvJInS=b06bAYJ&&*iZPozz1Kubn4F;^G0KO=yJA4-oUD`XD)E zSy>-IyRk-E57w6D{nx}e-p%pixey=PNQbXyn44$&Ah9NzYGEzrGsF(g-f#kwfOi%R zip3PPlmi!+1N^EO?7WQwH+u%&7$-*JrB8_s(J>A@Oo3V@m|!tgf^m!r?>V_@OPSS- z>NG~*adO|7_WKbiNm$Tx+BD7EpfV*_~i&O303zeGpkG#>W_mu zLle$hbWJ12=#gSQL0HdZ+{%is$0?(M9#4ErOZ>KAGR~T7zGAM?`jVT>v}P|K25l1HV3nQavA z__P>>w@iX|ivt%KfRNVU8JKP7RbifK0C@(_IF+RG|MmxL|}rwTr@S`1nKEDRkv)n5$xkoMZM;5&fPsM!U1Ae-hpsfuYF;L&$c z0nB&d0VcJo1#sUjJ_%K~&2$LKdK{VU1xW|d52lMhqV@rJ_i*q?cN{Yl>QH+;Y$lY~ zQU`0PvCoOg&eUhL)bqyF`C96<=f!j?#$3H2t{te?n@AiwSFDd(a$tdHAT|BDx#Cyoi9lxhLHNi*F#Qv_ z!F;i{Gj)QNdV9WD*O@v;OI^D_%yy=}qNP5z5Of5(qj!LjI91CcMwRF-^eRWFeT&3P z=pq;Db5{H!4qgIw*HVAbQa@M%J&BfD31`_sfs1&m9W1Y<25YHVOJVc@sZ@Y-Q~)jN zYlC+TqhD9UkKPIaU3-~WOK3ufCE-y`MG1Q78OwAJ)DPkwV1``={Xq`{xNAA!*~`Vx z(Xb%q1?b3Df)c~h_nR3IPRb zh9TvM)pM2jCA!JQ`j!>Hi4U&^D{86#XsOS<0<}s@4a7%F!AM6&h~fC|N@$30;*2%m zCoMnTJ^#iUMwJS6jS8jtrhZTbebbSU%@W$-tWw=AZLCJOOe=*^eKErgCyW;(9c|@Kix_FjE8RmA8H7H9J>j^@Mj#i8QKypHAYLlwi#MHEwzr8 zx^fFN5s*rS`H2dnd9jW4QC@5=JW1#z;mqZtECidnmdAsQUaYrGtRswPU{Vv&nDWqf zwuz_FykO?brKD5~ymlu<Z)`kV(slbmk~1gjffLB@y^; z8LUcO+5=M}4VUS}k)-RJ#Sr}LUNOd*-`trG9O7Sx@e;zFUx(0r$b{4!_;~Q69XNu} z%0fd!OwKEz;=vS{4(Si|dd%4-}Q%>8;8`s`%}@Dk5p>bQ+Z#IJX~vD~9?T zw!k!60}Xh>Apa0l%1=+gq6Pdx+sdfrUi@b;EZ6eIdA$UR*o9%WI2i?eJ*ZC1=Uy;D>M=* zz`ehKr6nz|uQ|{EGIS+c-Y9e4@yno)miL@FZ{!sSCCDR!p{9^$nBA@jtC%Z=op}0H zV84wO*Ic=|n!%OJufZtfU4}bW4i3M5O)Nu~xdCo*VUOGf3tz@}u7d%zyx$FZ%4Nz6 zyc~>gT!T&8T{oap*N{qe<|j_2=}j@tnHOo!yL}T(rIpJxQ6AT_?{W&PC4S@<3EYF(fAsy5uM74kH_ivfR&cINK3ta56rBk zzN)3J{uxHjTIzl+^|4=I(F;;()f-d8tBa!>}295JwX)VT3Q!(0zJEG068 z+XUSHchQD~aJu%NN>kbSp1U>J<^(MB-#47TU~BQUZGZXUkUzwo8UAo0Vd_#_0Q}gR zg`1B8Wx(J3OwB964k!iTdw+!Pi=cs_rYL%_%AUG z4GzcYs#FjA|IMh;W3wIqhLPA@&L`y`$ayiGoS9Abe^n})Lpa!yR*2`DMqkN=kLL5Qmp=bv1-(mnn;Mjpu0)EL?swp&J#IE}Sv789TWlUwM z5D%>^^?~D6gq8m`y>KC;hco=3KXS!W4$DtEMX{<1rK_eu9 zPUO%XZqVl>X&{`jq5|yHa~E;}I>}T3>WwJ6=|`#s>~@lq&V>eviB=2cWdE%?jmi;T zoMEhJ@B)7+3k5{7 zD$gs#UY(S7Q3zfULGIg-WSr9f#e8qD+e>-mE?u`@wHtSFMk z-akQ7KlChTxxfk;lNrk5&UJxX-*+8X>(2>wBXU zp&gqa3F(1RtR34x_%Mq1snZ&}9esRNhdjF5%!-oUHg%g#qRic98vM<>%^g6PcAJ?| zQV%>fTIwt`BO<1T7!Rxx6!e{G*f&OM6YH(-Z;sV?*dilUAld0$5b*GM-70iiPK> zsr~opWu`NO89$!iXz+uKjt}V@ghL8rpq1upsi8I-+GvUzqBx$_x3+Isp(7PP!Fhafb1N(Fg z5sfrhlahf3C_rjAKP`fHB}<{a=HbtirTW(D(PkHc6B1IOrHP3)wfJx7x{sUSwfXq?qRO0nol* zfQEAL+H`0{N^t+4aKoYJN+ld$OP6M&Y0)@84>}dS@DxT5pUVK^ljt9D(Kfe^^ew$a zNi^$759vv{(FVI48_9z@2DGP#i^}kpOsNSuAw-Al{#jB}v@2R0vY$2#+4t;lHUirn zi?g8rL~k+eEUz1~Fk}VeD}RbP)(_m>MaQ8R&F`eLron|Fm)J#gjeR2W&Pc-%8++3+0s==Xe=+H0* zZCYQ4j;t>|hq5^IpbkyvR2xvJA#4Ni;s#PEm5PjS9D0#E(JU~08%kYJcSh3xO+CL$ z3{&JpLunQ&VflDkBM6*g%FO?ejvWv~6}jC=>IL(#W_ePcFol8MGJ;HUUCjfz2oqA@ zVj6?scbGXkH4MLRyXb`ru2&-QprCWtqw+3Nifz%dBv8D#$ zxK0ty0?}3(erc=RxjERE$JUbO(neG>7Uu_9vaqd%q@cK1=8~-~q%&{k10d^3>E^iJ0<^(fa!>sLD z4tkShOy&en7zr9`yKx+45Rm9Wyl!g)G@@f!9Ik2uRcRfg?tfAzxP~i@+e$moKAwL{ z&)>sjz&i?o*sfTr`jtZI19X~8`guFZILRgbKrgr}){CSD;)FSo^riMpQltA1x7Xc& zr#-m;XLt7}bpZE2FuVVZF2c{;{qRd07(*5hg618e4-CbNJHrg?tX?oUjzvOlC#k29 zOtbNkP9S4q91DkYIyNDW+9a{FGz1QZ1EoCFgrV?*&QK&F&JfiBIHL>HOG2Nt7Y3Gr zam-KayGYN$M2<>yLFZD$C0fx{8YxU<5;f=si2v#$2lU@M+mzirsFPQR$Gc5jrWK?4)|4Vwof8%ggZ|P~2 z&2g7{11^J83+zLwc?oy}dmF1=c$@w(qC2YDv_DAqwr0~J_~XrZszb9PSg!euqpp#R zkGT#vbPgQbY5*AWCyu=`0I=UPtmUQwi(>{#rGg(mIuN=dAKayyTo-2#lA6JmFeGJJ zZt2)CTsBC`5km0du`oMTis9c`IKLR`d3pj1rY*(Lt?>NMilv4^8%E@|PNXI7{1o(q z@MMPG#=)7kr=TYJB(RwHQb)fT@5LS0bqsY!h@<;pX|}I0f-=PZ!$4gyEgkG##OcGN zW@NBO|6GipA0|x|<`ZO+FRal1i8F=+`#HcKuAe!24~K@px+=lVvG0wL>IkorVtSo? z=OgFva8&}_5mzESl^ik>O75d2L$o=Qu_V4S5>`Th0KIEz$eBYNQqM7DlvE9FHo1#r zA1yV9n@vO{C*k*Wkv?>UjgczD)h0$6cN`05InSJBG2qTPz@;Mv>tF61tmAomd-u z;TiBqo0@EGDq=FkbxXWx8cb;WPL^H~hEw)9bqb{0aL@!P#s92cdT>ozS?yD#OTzOE zxn?RLXHcZ&oB@e%Ow|^Hj8hf^v6ckF7lS%H3#Kfn$vVhqpOuoVo7^>f<5{UGY#0)c zX_}qaIc{Q_ZDN{P3^^N!er2%D3Wm=UPEuL%mg&Ipy_)Q`htH==3xqG3LNCt%g|0J& zF6!jp^PA7OE8p5G{Vpkc_wr6qp0yYRQ|9{eApwR%bV!J1ghB{1l< z(@@-Jj$}12Y-QoebEH^Q2jY@FH(|VIol(on!dBy2bYUxrT|FIIJSlB>@whQV299-I z)4D_i47Vl1F;M9vlvs<#T{W7@R-oo2IK!LW%b1OxsD&>K5bFkf!OHdmT_E^9Ud^zv zJoD9zM<;4mGdS`QS2H58!6>-Gs}`lZ)PDGehtU){U}m99J9bKtrhAp()3Va zW_jqHOJUGmXh63v54~cUbOaS8vi;T}q*Obh2wzz))pMp!(NZy%8j)1Ghx#O=svYU_ zOEhh7`!EHJ7b_z0k`+={>n3;8-CrTuNh{@Qy6d{>NGTW7Z2|${jwsq-R&SljblqNt z{^P8{7$0~+uUiGHi(eUlH@yJqnVRQTORu26xz&8}jrHJkdZzf5S0s^Sy!HxAgf&2z z2SDF7&^!Tv+VTP8rP*>_1#H=CE$p)t)OHKQ6Kka{LR-R6ziWF#w<9UxV#k8o%#Kar z*ARkv6sd(^qjl0cVF)3cg`V;P%wG>-I-OyrdcjcZ6}<`*OpIe+k#dE#2HW)8Ac+d* z63)xQGhUUlE&9<9T$@>IDWk1fE3fvWBX8J7se|>DyR|;pD7_?HFk9=UZY@&6#agF; zIf=UW%?iF_vR2e4X_Ih|S>i`8KnS=<+7 z@V?ij`Y0or#ZW3EqQ%fhebJz#1j;$#ZHL>R%>74>b_7Oa?Sym=a+KiE9D_yctd&t9@n9UISfEBj6_8Zw>j|Q zgV0zzxM^NzWHi$}k<3mD@xwzttnHTg;UOCtYouz&hI-+BZ%Xm7Tzv_Cv|~e8bc68W zYWyL|A)p7zbXSi2{{5D8ko=MnB%w%+xLUOp0TYLTbg8XT1tpoYBsgQGCa&t+hoc?|xDOrdj_{>LN->cUZN zk3&XBj+##X0Ages@4hi@V5kXvuy(CXJNLZrlB_&tq^+qI;!xBPHT4xS+uByM^zPl@tKn#-A-m8ivhF^2cD8QAwWnlK9UHuz3-OGcQVc7Q^JJ6i>V;jX~X0$y;ajTj;N~75>~7_=ejI zSP$>Qc}OaClzb@lmBpz`p|p+CO^WsMhFT#SO_>Z%B`>>auc$?sUr}QqHtie4fzD^% zHeZo)L)b%cMx0j3{H{uytaH5>+HN+Nb%oQ=b8*XSux~Xtm92N&y(Xzfqpk4%c;BY< z>ym(WKSJ%e!&L2^Cbj#ys7*mk?QL8G2v!dkuUJwk4!9|OtehvLq6&dHUiXz6CPw+e zib6CzYj#-wTw8WUG=_{A$#!Ys65V5Xs9v z=8pwJ6%4n%&rF~_V;5n5#*T5;Y~b>cUB6qp>kYQjTEn+)Nxp*hp}X%p`~vID@G22$ zV6_%3`?k~f4^#1Dx1}kbO5VB+GwSN)mF)7h6yvGnb6-Qrl=4d6{aWgSfHyt-HT4@w z&Hf*1-obCAJ-(x3uC-hx&nV6;?7q1#_v)XvayFP!(F0}f|%u-bD*=*<^QN# z-hczkkDj82;L;zZpRKkux7JPEEO$aG`r;e0SBI<;ON47B@5sE12(wB)7h}-ah=qh zH1hUu`m~BHKpNce-(waYC)J)edAtx+sx+whsTlGm-T0z$#r?)Qu0N1g`=Vy)G@`wB zBLn)-h;E!-UN=HPEYuoupfjSoJk%rFfYaKNT@R&m0xC*pqsuZu{$FY*{y~t>qw$YW zW#$&D%9wIhp&+KpNLN*s_{g~}c#mkn{ddn`e_#1ewE7Y9E;&!-U0JTY6vX6R?kex) z%5qK=m)C$Z%Im$m#XbGxuITt9WL*C{mGOv4M%V6^f|!hNrL(r{|J2<&=7{pw0$i>S zP~<4Nwyh!^Ef@4!y57+Sx^%Rc3BCFeE?uiZ_)APnZ#}93`4+SRrl(=QSL9sH6$V_z zT;V8D<<0^M%P7C9?uqgxoli)Hv8pz3>3k@N`64KzJYSSL#`??E{ov`y`N47w8_bL? ze=x%ZNMizcGm}XI7c)%^k)2~s15Rr!J_(VLVC}-?cD~xpr%t^x*vyWP?vJ$ub1+T2 z;KxJd6G9gp8zz%&8}>lfm@s)A8l6FpBdI!gjstc=mkF@0OQ%dPnW?_317|t<)sTw? zxYG?}v-}M?Gc(vOby|e1qG_-ok|M@C`bNn02~|3u+G(cxzD{+kqe_(ASb+D%2vs~a z8c1wn^ehJ0G{=!>xj&&tXILMa>7CT+opZbrOX!_r^epi}?=++5Z-9Z6o==h()SBa1 z6fdtw*5BP7(4v;y6Fp=?Xd}N5bRmAvz*lO?bA{iT5HBanrcr+>-km6S6vCF*mKzu+ zN*9OGh&I*|L#I~G8|03uwdKEkgft+S?6qsVX{XeaGmZ7db%sPiEQ%62(Al+hOw%j1 z0cRAqoc8rpn*6QMy<7=@K1e0(Vv?|yOO2)=CSk`+y+%{cLaAd^h8!)xHu9oOIi?C} zDd+i(9XF_W%$TLc_yUrvC3~5faNagol2tv-iQuNz?$ZjaBz-PN;Za#~t0?20t@%L0 z_i9!{cV{uJzruU|Q zDsEB7z3JDafkxGqNn0v!ZJGhuks$?Vl*HE6+cX1?FIY^gD~BWNNp59BlSUh#3z?=S z4c&A$X(w?)uDsT3!7s}x*rC4s5;~d5*82=3xkR-a$ZsI@7d)Q<_gVaXb(UJYStn1v zBFH$XF}Q)R1kP+MAGbzkvFLLu0o#^My$3cOGKCTm;W%8F^IId9=h^@_|Q7#>3x`Q@}Xk!v(;W z^Z2Pi{?|I(oyWuG@^ivC6OT}x$8dbSg?yUSv6j%i*tiA;Kv*GJ*m+JOo3eGct~_b}YMhg{JY-r-r!)%PG&4Ntq*CNhWH0dW)+%Wi%Qll(h9eHT;7aY zaSqYF!2Hd#*`e6}z2v!QD7R8%Z^$Xhrq#rfq7x{_{d>!Yg_$^}4@BWK2JlZc0J5PT zCEz#u$WzctM$A7=&tA?-;5APG{bGWR$7i3AC!jKpP1mtIICf`W9ecH}JQ=;uuz2p1 zkns+eAww@%ob6>9-=GN5njBGX*bitlV}jWF$v3Rux*N4`e=zDjvr#j3cHiP3`pYNL zx6G*ihMcdt2GIj36FMc&tjLty;4&VnYX->wSi|bLh3bxhaxL@Go>+WiAoRxZSb)Vo z_>he8oz-aEd61ms{sDzFcw`E0TNluSJ@T+&!~5CB4;t+DqI@<{I^3p-K{meTp`?a} zM_AzXi($~lWE6V{-84M5Se|9=ea#Wv(^djeCm|QP06b~u6*k1d?w(%CGrSi0_Edx$QZ}C z;WdCbxsb*KU03>3r7W`!;#1dtr9X6fUYq%6)rJTzcm8% z{RBA7ms3<7)OPtu`FX2Q*CiltV@U4<=K+q6(R<@uy_kTrN67^U4m{G0Kts;I+`d;v zQTx)m(zzma#o&HJW9j9tf0HqCbNu8VVq^TxXt|c@`eIYi#W;dYC%Ta#Z&YD3Pyia> zAl!HibkX@tIm4xYk`MI)mNCZ44ZU7mvm$b z-Vr)UhQqs0xmwv%4>hVT?V*G*gdqENim{6tf!j^~zjRS8nTk*0zb4C*JxTQ96gk`c zQ4~8qF-1;;hpjvcv=}#-T490M_sym`#ZdD2F<45fW!aHkQbrK_1M7U@JtA7RFAb;Z4F%D@GmUYR;XVv z2uCC242tE{`#B;K0Lq?`*k?fJzvPu$IIKPeSXN9F}@|$+gSpf%{f7d-Rzn4@PfrP>v4T zzkI#{G+!Qq&NGmIt`0iGOo!7JfE_8p1pMRz7!-ZYu-F3MbVawgGwSOFSJ(5hMq&_i z5?-_rM0mO$J39USLb;h$$#FANlSOiCWX&;|siDqE!S5}S6Ood`hMUogK_D@Q4+a;@ zucFKx8o8E6dKuVOSOT1rb7;h@ULx;Ctr-eWv%|o;1<6nG&(lkA=xsZ!gFVTiZ!869 z9}2~H;olm)m}T;OG@gU5Ed$UPMz4vHo|nO$K}wlS$% z`h%Is(oHY(8*}j6TLJrX4!k-i)x>wV%Ck{GE^86DY=az2E}oI5q*(NFKj+Zk3fwNA zLA5wEU(Po z*d@2TRX+;iYibI^s@b+K>CJFKg7-C8Jm8fgPW068qhm(*w0@Y7;@HSTywu8vmcvKDIPA#)#B&N&YJ z=^+?q9(#n=OY(tLxb3h>YuAk>3SwFx;u?5fIrLEJJtUPn{(MVri{QNFjUyG_SmJ_S z&Go*z_ywWowy|Uo{xhbfx79@h@=&hJj>+3cb>|vzT9a~2{>vIz-_5yXaZ#v-i;lxg zfctiRiPN`%c-?WihNp65?*h(@l5*NAzp-3>w)EtIA=#vWj{|sRc=sLX?gHzxU~2nr z#e-?~yK)oMyMFm~e$PT0Og-xx>%40)Q4kBJ?%ZPkw_tkhJ^5s1IE6gww97(uw3j7! zF6Ptt!f83xb$4D$&Cyz&)xo2NFUvbZVab8YFXCL9&i&v;;KPcC;6vRAx z;{OxR-o7BeB?v#@{Eyt432(mTf`04Kw_g)VZViM%>|5o#)qp(V>ei@_^-U@R&e&af z-=uQ9{IUEFLU9es9~j;A6-i?amj`a^10&acDhgs=h-koCBvQY$eX1Ilk%7NgCdQ4Q@x?Iab=+cp8ADcx88Etk1-sWlmQvRkov~dnJapQH{f`M zPq`{*2xwUYHXfXJO&?V{&Rmnj1nU-Vc;|Kx-!R|Zz%*v~H3edWxqS;BaRd4z4+ZI9 z<2Wm*bu7k$4cJGqw=|#~gvF5c8i~0SJoHPD@6`rur+w9zvQ?0mRpO^1@s3+^HR~;R zap_L{_hxbL>*C&WboxpT5zsBp)sS_AaLsWt{QEX+L0SD9y7jZP+pCJRd=$7f%{$sZ zbPoQG@4k`S3&_7A>-dIz3tA}fX;1QALMizJRPwwnZ!iIOnDCwag#eGJ0JAJyrNsy|bXe(+SL_{+JsZqv>`|U3<|WES71jm9pjZ%& z4pN%phE}Da@Dh>Q{L~&nfsvlZ`>aZ)*Jo-uYA=qBRKgq)!OC?cl;VG?DlLW0geF`Q z?jcvkqeGP}RN4s7=&w|>mb!;S&@3ec-wai%n%jZ5apf>20TyC`l6yOF2oDca{==T? zl`y56aZfduX;|uzs==4RJ&9FVU5PVqo!!9CR9C{`O#r7v#)!P;B_e;I5gAV-vN8$o zY}f1Xnk;x+4P`8`6y5x;9LwKt;*VV@Kh($0)U}U5SW>2O8n^zuPfNQ@Ei?By>Iw)KcfrHIKb8(-l7(tK`G( z%aK^+hA@gU@Ncc-I2*?=af-h{cKH&ZE^CQh6O=FkzDYx+T2)h*%JF7RC02lwJ~XFF zq9G?eQHc~F&}q)p+B}Ecjw-9I1PFWak=n|~@O1@}AJ#<|#NblC;h-if>);#Al+e{= zAao{=HZhj2dZ|-5HbwawUQwf{hN*zM#Zlc{P;k~I6$t)Iq5j?V+`sb3T3S7HDzDJSE>r|VotLRuplIoPAy;-^jk$G@z8|V?7MVcRlInpR2A>bP$JPaxaLeg z7?1Fs3}roP&{%tTaEGC*%Rb=@8CXLcs)RUhWhy^F|J<0ZG1qm=kFTp7MW_eQ&vDDo z$yI9kS_d|Ei>DEdlq58?F&iNAGZ6Ll;sfz#jg%Jd1MXjXju!ZRN8WO(9Z(8%FMLq;sMohJz*B#fIhs(7jGBEDXtM8Qa9L}Mk>*g{d6 z!fgW`yBkArx(jq0f8Io?gG!ku+9@2PCXhp#TsIq(;Ym%E^y>RT5bbcj?R8=()&s*6 z4-J%H+sFEa zyEn62f(^bj+n}ND%`dnO+)9?=3oVt7=2JYsH^%9$ls4#rM|FS02U}HGUGQg0Yo)Q# zpH!-F+ZT?>t(ESACtYr|QRABB|7GRkAa)v&M}XKd$7d@xw+Jx%y924Ie914j`~O?ZCFT z)BSh4o$@`hc5C8R8&7pql3?8A)LA=lkf-~w8?M_4YNT7?GCZe~($=i^2z&#u(ENMQ zdl(+lxx#vb13&Mq)HgbiiWF|^hHG|FK6e-AHV*0vx-5KzE|a?|1@48*@VTx^3$re- z;@ED`^=xl{P}$CViO!euzAm(t9v?QJ}vm(oc1#*?NtMt13IHq%uE(T7H_7;^;Je8Yjjh$Fu&hV zX^Rrgl$+^>g1375E7jc#mf>yvl`ONN8sTsIE2*e)Q%{{v1Khi)!j^&<|DZ^TF~&HR z30Bb@{}w^JilUp+fUp=u<(fV>NGU?r0Uk7cN@;{_W=#upO$XpHgO%p)1fVY*6mcG&<1n=rd9!#hX0wr2O2k5-zZ zKTK-L`(OwH^UPnH;@z{9V2npAkrf;;u{KQ}?cSzonmHPdQKk!MBXcDFeyrZ6S;i?{ z{j8DA+^XrQXP|!9#JeZE^uVojUq&`#qbj%3WjJ86(%$UM26)J1r8TT514Y+vI2V_Z ziLW%J!a75JEuNw@GDa;GEZi39*gHk3?Snu#+V%QR*Og71u3YrB_IFj54jq!r;@WVV zSukoC=1JTVBJO_}&c?oAo^ZDzCJeXr$L(KGR(KNU{tHSSvpDl{?rbF;dQ=bAo6D^C z*6a#fk3~$g*-E%;zo3cc==7p;(FgTsMzqjmHjU+t-q?A{+dh%6yPER0s1Ky^^hHW4 zerA!92U9<{I4acR=ye`PZq&+f++rosY>D%@=VB!edRq^cILj>#Dlqccx6xFFeOz3dKbwa3;4!&Aq^Oy2}gG5)Y=zs zT|pV|U!fEVO$q5dl&AB&3`@s^ou#YJqBCKU10U7#!pQ&yN|aOJDwxDmzXv<&tWvCk zFqV?_@1c{;X-tl|)NwdgD+`c7J`)XWAJg-nr@G>uYr!fr^4Ut^)wRkD1na^S`?!u> zMX~;dlo|PSdG?R>&>z8js-ysp-UzDiVbI=sVGey^qXL%`Pczz2=-DS(0YeH%qrXVo z1*dOTLba(@ug$>EdOP2xaV*3Aw<V@q^oK}`F2*N^#RPpP*1 zaq_?O>2dN{I<@dA8Z*#!KJg?GJsj44p5LbYgl^~4U`(Z{ygu@YAoMj})!+txJbg!p)ISL|! zetu-wPGuEB1qEyetHEv>xO9D^*KXyikF_(A!nod5hTHB_(#^HMH=eZ*)-0YVFpl`N zzVq<{)_3~tuWPA3>pzmb$qX62^-6u)s^j^KVWo9`iq;;(A=Vkm>S!0e1uwUQM4FSNq2qubH7uXIfOT7hTq|89x% zGhoPA_Kl)g42^dwe(xJt(okwmr0V0 zl|Pg**5p<$!>Y4*!5^?h)3uf9To5h9I_YHW`#`DZsbISY(3TG>r{LiSN*hlFtN#ft z*VC+^cA&_}u@yV1>Os~$f5OP<#qvu^)lhOP+C5tgL^nBLv=j{c+3p5d{x|d>o6UO6 z*JGy?*Z4;%@>FpCKVZ3o|CIecGGyLu|v8>zYI-*O6GL~6XJf})Sw6a}_6MU7EXJljWo z%u~UieAId^cjR^ za|Xv+t9o3phP83Adl?=Vq9&W?La}&zh*}fHx6zv18SpHDHgk+_!)A_2Rn>~Fx~9>& zP=IqT)NfqT*r9Hpci7526o&UyRcm?@^iEYZ)huWW93QGCqE;RSE#QK#53R7Eu*CH+ zR1G&SacNRH(!$gLc*&{_o7;@22F_u@}Y;^w>70W?;MS{Gm9ZhMIte za+1%~Fo$6&UR*nZ!4sEZNotrmKC^IMl3EK6H~~lZ!)O`!wIsEoYvUQT4h8CU zXl(JAr}_8a4L6rhF?kc)vW^0N=~R4SG7VR%#I9uZp(Ijn3=9dc`DdHU2P3t|M6b%n{?<%ALmN+%5VuOcp*w%A)wXN zZOOQ9mKtPi^3Q0#Bi)W;SeCj(ux@u(JFt%0TzK6q#3#Di+wsymYHtq(m)8a1-=pO+ zwG-0Da-5Tg_bj$Eg~AMIV;|=DuCDr+fUden<7Xy~*5{~_VExfuqeHoBmT;d+R#lVi zvaZpOZSj#0r0SkZ_O7pHAo!TP@#>thBtBIiJn4bupQK=oathiSs7dYx%kahqYKnPz zI2~VY0L@}%q1O8t7pYPUy$tvp7SaJfwBUyus?|aaRf5VNZUe39*a?22N@P{n?P0LJ zzC<;oky?y;6|yC&tIY0?6}l}^HPTk62D3c6I`tnCwM8dh{E>@JOB%yV>#M-dBk+QzFhsk~kyjW}o188K2f%ug z_T``@oDN@5;`(`7P{RA0skzW9?{2R0kA3*HGwJ2i&NxvYk*{tOVhrfW^3X3Az`*k? z{9%=v=O|C3$aqH{jOXY)h$o(@Rn)}%!>0`x{i6C!%w$V6XEGb5XikxnSpP#tZ<)_ zN&A!_a=N(Ruwg~Ri~0>8IjDG;+sKT{A8wo4&c4o43q8Zc*8J|%&a~cCi8;%(oQCVQ zhMwgBGYtKl%RaN}dsrbJx!<)`r^2I;dOVyi4}GT%G?r&^v$kOSZ*|*i9{y7I@NJJC zzRf-SH!0f!Pj9D+k?u%vGfAXw23A!uE`)J=KzrI!hVp1~;f2>t5R*}4d-gSv3J~7V zPHl}c8BHyAOf>b_`LaBdtZ%O-L+qSsujZJ?Bi(RN2Q>@zXs%EGlN*x#Nu1?V($XaX$| zZgU4itdK++E5NQDx@LB%iIeWqyddmfcVq!Yw)A3OQ4D zJ&c2gjvc%V9-io+4ITm?S8Est4_^~e;92|*Z14cTWIUZplleZKzQN^X`Q?5ubus>Z zyAq8D^-|4uEnWhZj8|?Z5)}#EsKUFznXJJ$e(ME}g%7cSgZV>dhJ_e{0{JH59(~j{ zUbmMyYEuE*UjDd`y3SWv&nS{Z8J1s+7N@g>6aCc>d?Df}SBm+~fN@+XR%iNH-*)#% z@esAPIYLk1RYTNx;gsePW1I6HMz#t^XbSDF{7atdH)8y7FJ0B|%pPy!S8TA{@is0R zs`e1>P%Z3%p%y>eez-|A4__S&1A%~HY6yC}13Q@IK^3w|Y(DD!ZwI;p@_KxQ#R`ah)?Zr9Pv zwNL{CCL(S=R^1GbLh2Gmj)MtcYDd-zK;0;H)E%e#320GAw|V=_xgc&hd})R%`|@}- zUqGcD@xN7->Nq{s5(zhO2wh~`kDE?V8^Q&&XC|o2;3se*tPL1>;KwJbd(ctF!uZ7V z(mjlYE{}(YIXonlI$oTlo)XZfl%)61;H3`JG`1FJ8BhM7X;^6`ZI-h$$J7#W~` zoxFsPK^UrFh-1kNwXzTD#HBy^ysBm!{OZ9m9+FBOezVj?2n_@Y%lmrDu|%*PIi?8K zsRoM)u|9H?>&H_lhPkRQ!#O=Q^hMSAx{?9L>%oZ^)wR~=U9Ae&ab8l>&7I!@yzeDg z4_(wr8{Zjwzj>X!^nNdQ(t5v@bJTES?{~2yRqOdqwD*IR8t_kEtig(2db}oc)p@49 zhW9~wV?Vc_Xv6xsFMtQ#YiK-IO~8@!)M#{)MT+ql6+wZ4_v5Ma)IzWQ97jR;(qmK) z=c)UA&~+98jc<-O#J95z@!)h1Nu`eX#VV4}uaAg>pI1{c;S-nMMuU1YG+m*r>^;*0vaD&qdtq0I+q{M*6*kuwear!UgMc!m>%&A=Zt6n zQq}pn5d+K+I38^5AqkqwQuS12)cFzO##t2-9WY7vE-u9|aSL6s z$2z*RTZ49YtD27{bvCV&)oB1iFb1RXm~Co3PX*tAbTrp{K}W`R=(#6)#iQ6!!lJ7 z&?O$JjrROck?NSZM_uiMet3lM3;I*v!_?oq?oGZ!3rT8miKT z)wrkw|C1iL&jGbPit9paoYzk}4A@E4i0)EeZ%;u?j|dKQ*10KfsLt=S7;wfqSI%oW zf4l*s0o3*pLXP>E3famer0Z)r6vTvV-bHU`wbybwA5yC#VE`_DM>T(&#oKE+oM}Iu zR;lCS+iE8tVYGqBBc9yxL}bA+H3-3nng1`6V9UE|C%9{%)A;X#U=XA!mflz2cbt6> zDiIv>*2(b?*Zc?L5RoGBz!Pe=u){!z%jNBJeoh0G`zVjew=S=6%{ZyoBm<7uq^l>@ z>*y@6Nq0~EZ#60H1GN>p`G_E060efZ;F>8&UB}H7#Des)YfWl%TCYh4Tm@^=JEzrK z0+PFyU)|RiQX&1i8mqhO7mp~23F*^SuSp(0B*QA#3de+Vsx>s=t$!-f|4m(58w^n! zr~d{E{84`R;8ze6HOZgwt&_`s)$`BobiO!t9h#TRlN*QdZ1Gq-Boy|@+Ek}bv1aLkh}74s@rd22adU5t|yOZ{3dpC{7<0k1C5 z%~0x?tyqToz;cl;!J|Ij#f-jyIow-l7}$+*4UMZ+EYA6t0mqxJMgf)$@Cf(y085^8 zeWYukoJ-WFJZP_`@$f6O0#||GduB87`a(TdJI+59Ld4wfeC?aIFFF|N`clvhoGQ}L) zjZQJOMK6uK>&C&w!?gPJ=*CuC;g=3AJ49O43d}kuMOt1q%{o_rcE*Y^n`le?6IJ*T zaH6x$iIEmqAd9jj!)qv_C1)>6^E9lp*wYRt&tqsBcoawOReaP`zJB51hn1kQ-Fyo^q8 zNBtFNQ7sNGESQ(SRMRxxvfcX7RfpU7pLk1i!4KyrSe%~&x~&`FVK+Q8!Lky;FN=bj z5WIi0s$+mX=!O^9v>di3c6SNo+ju}NOCxy9g3#9s6LW zenTuK-;4E(!@{>F7&N%Rvz*}`jE=#AYmgCQfZ-5sPAH4d*c?a$px zuc%vco3Ny%UeU`Gp8-?R5ZNo5^msXUcE2+OMyVK*>)0qrVDWc1ThMdw1{ZEd!c_(g zgZ656w&*E)RT+gmIh$9o=Y~OzQZ7`-4@cD*LKXgCQe`WK!w%(Xt`!y|1yw?qy^)3& ziUi%K(f}iNtrscYIsyf2^vq-Bg_E;yy#ASN*6ZK#5pZ2mc2O2X&COmN>oyvmP(S3p zl4AZOEpZEX51qmvN5k7H?gYa5Ihl?oy0I~HgbZR)W8q;Oa*!Zw)G>przw7sTX)NlV z6U0T0gORG5!yi$Ejh4E<>$-=>N!?$^!98j>q07oLuoiV;mnUGQyH{R!j@4&Co*J)f zrQU~HxV1KFg^e+3iOgTR4^_wLs{O{J>L`(5x=EGI8V^P4{kqogq*Wji9Ba}N2|hFd z#;X-V6~;;NY`S1D-ZLNlOqhrfAT;x$Zxc!8`rOP^$$F~Jy(SZ4+A6rGOg7vZU5^^} ziS|jfg2uFHW%4h)=>9~8w77)=R}wXQxvpqDpm{b2jEABoz5m@@)-e~Jz&HW^tSycX zqjqSQUu(INuy&`fwNq^%A16^_LeFe1pQ%JNJ2(8B4O9g~9{MwJ_PyN1uf0t4ohxxA zk@d+O*;Jb6O1K5#wtSeY2Ia1LuxmFqv;c}C)Lh-|P+9&0Lv+tkN$n|q@*mvh=osDR2`KHccU-?6td z2C@mhqu6S)EK-}1D@IB9OQWQ&{Itd2>)7x|V3@igmqq|yt@_g<8GiE-?o*GzGDUqu z+&o)fhI1EFt!d$n*`YFM^qRXIL3Ye@mp#N5*%UQyb#0iKyL>bg_Nzy8#ajr|l!X-V zw)U`3%3)}WFUxc->~i?avb0%Hh5;OW3*}R`_feeUUea^X2ZS%}Hj4DTJ9Re1DC&7Z z9+*TrA=~HRC_rs%W8d@&Nnqs_(9Yah`Wtg?t$;I%+TG@V%=LcgO?10mZT`kwTuGE^ zgiSbJ3sv1c_A#gl#Ey|X}8CzGB|;4KT`vZ7|$ z#A}FDhxb^^AAyfMAT3a}w?g2VTuxw#Ujn(3Ah6gkfqGng{U?yEtAb>8v5hy*m#QGO zv)(wH60BxJtKpu`&r`Y>te(sfIaRY2)$padQNQ(nEr#|X)u@F<7s$5OV8RU|;ooW? zHL{t6h3;w_?eZ)>{cSE6ckR>AM^Qg+HXGH6*)$pU2eSev4EjIvy5NMViu$7|FSXi6 z-_1p_?>`9*OX`7Dkj5VR)7VAcq_p6)qJL_i=OOUM`zO8dL-JbgpQH)AfAZbL!&F{> z^j`%`n#DGsD$ux8RsoZqUIqFu1E#1$@8(*EjH-3oAqs55vnEq}dp`@eabrFrH?$#-lRez`5oApvU^Bq%7M*{ z7o;1S^thXKb{~2H&IGC73O{2fH{n!9mt5Nf*HrZfT@v@2n9T72Hz_RRH5i1S<305n zOiD zvC9RRL|Od~C{g?Cns*9K4?D*tJDwORjlv@DMIB%4gqZLN1;Q~+JcPM%yqJw? zVPB6&PH1{)NM}9w!5w}X=(GntVZW7uF?(>taM+uHLdgJK;lsdw%$pe4=WXq~UJRta zi_b8;CvDC zET8o_07)u_G~*q_7wq8!ki|weLT~j*A;m!p!tMdv#Dma9JzU5d8evvEMTDne;a9{q zh9fpe=X1hoD>@*fCH81~=id`w**V#yV-Uw88X?@h>=+~{N}7A`XKq~# zr*qkn2$Kn>L?KLc5I#khd`9B05)cCLi+b%!9Kw$T12Jr%b~~MWW(dMPbd-g=XKRxP z>gn7xI@g!YZfc6ERTxwbgpcP?o4DIS@ zgewFiag~LZMzDckEdr_=?@+ZZIL6h!!Y^vICW4@RgcM@36V4>Gn+VPjoF=Hn>4dhD z;5~xf4#M*UX9=Fi;g|L-!9FY(EuWIvMMpacE)qELT*cDRnGfQ+LEMXA4)$feH7Z3H zFGLqFKo>7R7cV{+FFF@5HYYDK7cVX+6_o=oqjGZcGIH_qaq_Zp@?vrEBEjUaB%Hh` zT)Y@uya=3}eix@6GegFmoN_0p+r_DN63v)PB|4&$)9U1uIys#Vr&h%UM4*$C=i?7bcmtq=<+DyT9w1F7W zLW?HIAs9j67&#Vk0Ku~v2#W|xaQUD%i6DY%d;kG&0B8j|ZvZq}DW?6E;2=RqT!o@t zqa*qRL8FhFL~B4_+KU!~zJ3tx0!?(aZwVTwOh@ERM3B)$(4$7tL@ee_1VMw*LNw74 zZy}aYGr?O3nx2Rjg61B)h2R~Oc9t59Q-!R{X`Bx%W*xtVTRJ$4sPkVMR62c7e68kU z4W}VeS!IzW7_#*iS)w6()gl{c$QmrNL56I%MV4g94p?M^4cSqPEZLAXS!5}O?5st0 zmm$08D@&5R{A`g)UKDouj2E9tl9%=tndIeWi%jwoZIMY{`dDO=mw^_UE?Z=hm;YE~l9x7Y`P`Fyyzlohg!+42w+il5LSmUZ!%HL$s0h zzV-(D3Hwp|&-P1NHyWOHBp5?5jG&a@0fHq2l>}P|UL^R0U_ZgH1eXbVP*>HNAeA7I zpok!gfVPp;=BWXr0yNrYOWQ<1@tC!P1QcsoJ4euwI+ 1: Increased randomness, potentially incoherent\n", - "\n", - "A temperature of 1 represents the unscaled probability scores for each token in the vocabulary. Decreasing the temperature closer to 0 sharpens the distribution, so the most likely token will have an even higher probability score. Conversely, increasing the temperature makes the distribution more uniform {cite}`build-llms-from-scratch-book`.\n", - "\n", "In this simple experiment, we use an LLM to write a single-statement executive summary of an input financial filing. We observe that even a simple parameter like temperature can dramatically alter model behavior in ways that are difficult to systematically assess. At temperature 0.0, responses are consistent but potentially too rigid. At 1.0, outputs become more varied but less predictable. At 2.0, responses can be wildly different and often incoherent. This non-deterministic behavior makes traditional software testing approaches inadequate." ] }, @@ -175,6 +176,11 @@ "cell_type": "markdown", "metadata": {}, "source": [ + "A temperature of 1 represents the unscaled probability scores for each token in the vocabulary. Decreasing the temperature closer to 0 sharpens the distribution, so the most likely token will have an even higher probability score. Conversely, increasing the temperature makes the distribution more uniform {cite}`build-llms-from-scratch-book`:\n", + "- Temperature = 0: Most deterministic, but potentially repetitive\n", + "- Temperature = 1: Balanced creativity and coherence\n", + "- Temperature > 1: Increased randomness, potentially incoherent\n", + "\n", "How can one effectively test an LLM-powered system when the same prompt can yield radically different outputs based on a single parameter? Traditional testing relies on predictable inputs and outputs, but LLMs force us to grapple with probabilistic behavior. While lower temperatures may seem safer for critical applications, they don't necessarily eliminate the underlying uncertainty. This highlights the need for new evaluation paradigms that can handle both deterministic and probabilistic aspects of LLM behavior." ] }, @@ -2530,6 +2536,19 @@ "```" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Conclusion\n", + "\n", + "Language models have fundamentally transformed how software is developed and evaluated. Unlike conventional systems that produce predictable outputs, LLMs generate varied, probabilistic responses that defy traditional testing approaches. While developers accustomed to deterministic systems may find this shift challenging, continuing to rely on legacy testing methods is unsustainable. These frameworks were not designed to handle the inherent variability of LLM outputs and will ultimately prove inadequate. \n", + "\n", + "Success requires embracing this new paradigm by implementing comprehensive evaluation strategies early - this is the new Product Requirements Document (PRD) - and cultivating an organizational mindset focused on iteration, experimentation and growth.\n", + "\n", + "The shift from traditional software testing to LLM evaluation is not just a change in tools but a transformation in mindset. Those who recognize and adapt to this shift will lead the way in harnessing the power of LLMs. However, the cost of inaction is not just technological stagnation, but potential business failure." + ] + }, { "cell_type": "markdown", "metadata": {}, diff --git a/tamingllms/_build/html/notebooks/evals.html b/tamingllms/_build/html/notebooks/evals.html index cd2061e..9bfa541 100644 --- a/tamingllms/_build/html/notebooks/evals.html +++ b/tamingllms/_build/html/notebooks/evals.html @@ -142,6 +142,8 @@

@@ -205,44 +209,47 @@

  • The Evals Gap

    • +
    +

    4.1. Introduction

    +

    The advent of LLMs marks a pivotal shift in the landscape of software development and evaluation. Unlike traditional software systems, where deterministic outputs are the norm, LLMs introduce a realm of non-deterministic and generative behaviors that challenge conventional software engineering testing paradigms. This shift is not merely a technical evolution but a fundamental transformation in how we conceive, build, and assess software products.

    +

    For those entrenched in traditional methodologies, the transition to LLM-driven systems may seem daunting. However, ignoring this change is not an option. The reliance on outdated testing frameworks that fail to account for the probabilistic nature of LLMs will inevitably lead to significant setbacks.

    +

    To overcome these challenges, it is imperative to embrace the complexities of LLMs with a proactive mindset. This involves developing robust evaluation frameworks up-front, fostering a product development culture of continuous change, learning and adaptation.

    +
    -

    4.1. Non-Deterministic Generative Machines

    +

    4.2. Non-Deterministic Generative Machines

    One of the most fundamental challenges when building products with Large Language Models (LLMs) is their generative and non-deterministic nature. Unlike traditional software systems where the same input reliably produces the same output, LLMs can generate novel text that may not exist in their training data, and produce different responses each time they’re queried - even with identical prompts and input data. This behavior is both a strength and a significant engineering challenge and product challenge.

    When you ask an LLM the same question multiple times, you’ll likely get different responses. This isn’t a bug - it’s a fundamental feature of how these models work. The “temperature” parameter, which controls the randomness of outputs, allows models to be creative and generate diverse responses. However, this same feature makes it difficult to build reliable, testable systems.

    Consider a financial services company using LLMs to generate investment advice. The non-deterministic nature of these models means that:

    @@ -252,23 +259,12 @@

    -

    4.1.1. Temperature and Sampling

    The primary source of non-determinism in LLMs comes from their sampling strategies. During text generation, the model:

    1. Calculates probability distributions for each next token

    2. Samples from these distributions based on temperature settings

    3. Uses techniques like nucleus sampling [Holtzman et al., 2020] or top-k sampling to balance creativity and coherence

    -

    -
    -

    4.1.2. The Temperature Spectrum

    -
      -

    • Temperature = 0: Most deterministic, but potentially repetitive

      • -

    • Temperature = 1: Balanced creativity and coherence

      • -

    • Temperature > 1: Increased randomness, potentially incoherent

      • -
    -

    A temperature of 1 represents the unscaled probability scores for each token in the vocabulary. Decreasing the temperature closer to 0 sharpens the distribution, so the most likely token will have an even higher probability score. Conversely, increasing the temperature makes the distribution more uniform [Raschka, 2024].

    In this simple experiment, we use an LLM to write a single-statement executive summary of an input financial filing. We observe that even a simple parameter like temperature can dramatically alter model behavior in ways that are difficult to systematically assess. At temperature 0.0, responses are consistent but potentially too rigid. At 1.0, outputs become more varied but less predictable. At 2.0, responses can be wildly different and often incoherent. This non-deterministic behavior makes traditional software testing approaches inadequate.

    @@ -379,11 +375,16 @@

    [Raschka, 2024]:

    +
      +

    • Temperature = 0: Most deterministic, but potentially repetitive

      • +

    • Temperature = 1: Balanced creativity and coherence

      • +

    • Temperature > 1: Increased randomness, potentially incoherent

      • +

    How can one effectively test an LLM-powered system when the same prompt can yield radically different outputs based on a single parameter? Traditional testing relies on predictable inputs and outputs, but LLMs force us to grapple with probabilistic behavior. While lower temperatures may seem safer for critical applications, they don’t necessarily eliminate the underlying uncertainty. This highlights the need for new evaluation paradigms that can handle both deterministic and probabilistic aspects of LLM behavior.

    -
    -

    4.2. Emerging Properties

    +

    4.3. Emerging Properties

    Beyond their non-deterministic nature, LLMs present another fascinating characteristic: emergent abilities that spontaneously arise as models scale up in size. These abilities - from basic question answering to complex reasoning - aren’t explicitly programmed but rather emerge “naturally” as the models grow larger and are trained on more data. This makes evaluation fundamentally different from traditional software testing, where capabilities are explicitly coded and can be tested against pre-defined specifications.

    Fig. 4.1 provides a list of emergent abilities of large language models and the scale. The relationship between model scale and emergent abilities follows a fascinating non-linear pattern. Below certain size thresholds, specific abilities may be completely absent from the model - it simply cannot perform certain tasks, no matter how much you try to coax them out. However, once the model reaches critical points in its scaling journey, these abilities can suddenly manifest in what researchers call a phase transition - a dramatic shift from inability to capability. This unpredictable emergence of capabilities stands in stark contrast to traditional software development, where features are deliberately implemented and can be systematically tested.

    @@ -395,7 +396,7 @@

    -

    4.3. Problem Statement

    +

    4.4. Problem Statement

    Consider a practical example that illustrates these challenges: building a Math AI tutoring system for children powered by an LLM. In traditional software development, you would define specific features (like presenting math problems or checking answers) and write tests to verify each function. But with LLMs, you’re not just testing predefined features - you’re trying to evaluate emergent capabilities like adapting explanations to a child’s level, maintaining engagement through conversational learning, and providing age-appropriate safety-bound content.

    This fundamental difference raises critical questions about evaluation:

      @@ -445,7 +446,7 @@

      -

      4.4. Evals Design

      +

      4.5. Evals Design

      First, it’s important to make a distinction between evaluating an LLM versus evaluating an LLM-based application. While the latter offers foundation capabilities and are typically general-purpose, the former is more specific and tailored to a particular use case. Here, we define an LLM-based application as a system that uses one or more LLMs to perform a specific task. More specifically, an LLM-based application is the combination of one or more LLM models, their associated prompts and parameters to solve a particular business problem.

      That differentiation is important because it changes the scope of evaluation. LLMs are usually evaluated based on their capabilities, which include things like language understanding, reasoning and knowledge. LLM-based applications, instead, should be evaluated based on their end-to-end functionality, performance, and how well they meet business requirements. That distinction has key implications for the design of evaluation systems:

        @@ -532,7 +533,7 @@

        -

        4.4.1. Conceptual Overview

        +

        4.5.1. Conceptual Overview

        Fig. 4.2 demonstrates a conceptual design of key components of LLM Application evaluation.

        Conceptual Overview @@ -613,7 +614,7 @@

        -

        4.4.2. Design Considerations

        +

        4.5.2. Design Considerations

        The design of an LLM application evaluation system depends heavily on the specific use case and business requirements. Here we list important questions for planning an LLM application evaluation system pertaining to each of the key components previously introduced:

        1. Examples (Input Dataset):

          @@ -698,7 +699,7 @@

          -

          4.5. Metrics

          +

          4.6. Metrics

          The choice of metric depends on the specific task and desired evaluation criteria. However, one can categorize metrics into two broad categories: intrinsic and extrinsic.

          • Intrinsic metrics focus on the model’s performance on its primary training objective, which is typically to predict the next token in a sequence. Perplexity is a common intrinsic metric that measures how well the model predicts a given sample of text.

            • @@ -1008,9 +1009,9 @@

            4.6. Evaluators

            +

            4.7. Evaluators

            -

            4.6.1. Model-Based Evaluation

            +

            4.7.1. Model-Based Evaluation

            Traditional metrics like BLEU or ROUGE often fall short in capturing the nuanced, contextual, and creative outputs of LLMs. As an alternative we can consider a “Model-based evaluation” approach. A common approach is to use an LLM as a judge. This is an approach that leverages language models themselves to assess the quality of outputs from other language models. This method involves using a model (often a more capable one) to act as an automated judge, evaluating aspects like accuracy, coherence, and relevance of generated content. Unlike traditional metrics that rely on exact matching or statistical measures, model-based evaluation can capture nuanced aspects of language and provide more contextual assessment.

            As discussed in the paper [Li et al., 2024], LLM-based evaluation approaches generally fall into two main categories:

              @@ -1250,11 +1251,11 @@

              -

              4.6.2. Human-Based Evaluation

              +

              4.7.2. Human-Based Evaluation

              Human assessors can judge aspects like fluency, coherence, and factual accuracy, providing a more comprehensive evaluation. However, human evaluation can be subjective and resource-intensive.

            -

            4.6.3. Evaluating Evaluators

            +

            4.7.3. Evaluating Evaluators

            We have discussed how LLMs can be used to evaluate LLM-based aplications. However, how can we evaluate the performance of LLMs that evaluate other LLMs? This is the question that meta evaluation aims to answer. Clearly, the discussion can become quite meta as we need to evaluate the performance of the evaluator to evaluate the performance of the evaluated model. However, one can make a case for two general options:

            1. Use a gold-standard dataset that is used to evaluate the performance of LLM evaluators using a “metrics-based” approach.

              2. @@ -1298,7 +1299,7 @@

              -

              4.7. Benchmarks and Leaderboards

              +

              4.8. Benchmarks and Leaderboards

              Benchmarks act as standardized tests for LLMs, evaluating their performance across a spectrum of tasks. These tasks simulate real-world applications such as answering questions, generating coherent text, solving mathematical problems, or even writing computer code. They also assess more abstract qualities like fairness, robustness, and cultural understanding.

              Benchmarks can be thought as comprehensive “exams” that probe different “subjects” in order to certify an LLM. They help researchers and developers compare models systematically, in a way LLM performance is comparable while enabling the identification of emergent behaviors or capabilities as models evolve in scale and sophistication.

              The history of LLM benchmarks reflects the evolving priorities of artificial intelligence research, starting with foundational tasks and moving toward complex, real-world challenges. It began in 2018 with the introduction of GLUE(General Language Understanding Evaluation) [Wang et al., 2019], which set a new standard for evaluating natural language understanding. GLUE measured performance on tasks like sentiment analysis and textual entailment, providing a baseline for assessing the fundamental capabilities of language models. A year later, SuperGLUE [Wang et al., 2019] expanded on this foundation by introducing more nuanced tasks that tested reasoning and language comprehension at a deeper level, challenging the limits of models like BERT and its successors.

              @@ -1343,9 +1344,9 @@

              -

              4.8. Tools

              +

              4.9. Tools

              -

              4.8.1. LightEval

              +

              4.9.1. LightEval

              LightEval [Fourrier et al., 2023] is a lightweight framework for evaluation of LLMs across a variety of standard and bespoke metrics and tasks across multiple inference backends via Python SDK and CLI.

              As a motivating example, consider a scenario where financial data has been extracted from SEC financial filings and require econometric analysis. Tasks like estimating autoregressive models for time series forecasting or conducting hypothesis tests on market efficiency are common in financial analysis. Let’s evaluate how well different models perform on this type of task.

              First, we need to select a benchmark to assess LLMs capabilities in this domain. MMLU has a sub-benchmark called Econometrics we can use for this task. Table 4.4 shows a sample of the benchmark dataset from MMLU Econometrics. It consists of multiple-choice questions from econometrics and expected answers.

              @@ -1534,7 +1535,7 @@

              [Hugging Face, 2024]. Its integration with the Hugging Face ecosystem and modular architecture make it particularly powerful for evaluating open source models. For further details, visit the official repository [Fourrier et al., 2023].

              -

              4.8.2. LangSmith

              +

              4.9.2. LangSmith

              Let’s revisit our evaluation example when we were interested in evaluating the quality of summaries generated by different (smaller and cheaper) LLM models compared to a benchmark model (larger and more expensive). Recal the setup:

              • Benchmark model: gpt-4o

                • @@ -1942,7 +1943,7 @@

                -

                4.8.3. PromptFoo

                +

                4.9.3. PromptFoo

                Promptfoo [promptfoo, 2024] is an open-source framework designed for evaluating applications that utilize large language models (LLMs). Key features include:

                1. Automated Testing: Promptfoo provides automated testing capabilities, allowing developers to run custom evaluations tailored to their applications.

                  2. @@ -2207,7 +2208,7 @@

                  Prompt Comparison R

                  In conclusion, Promptfoo can serve as an effective LLM application evaluation tool particularly for its ability to decouple several components of the evaluation process. Hence enabling the user to focus on the most important aspects of the evaluation given the particular application and criteria making it a valuable and flexible tool for LLM application development.

              -

              4.8.4. Comparison

              +

              4.9.4. Comparison

              The following table provides a summarized comparative analysis of three open source frameworks for language models evaluation we have discussed: Lighteval, LangSmith, and Promptfoo. Each framework is assessed based on key features such as integration capabilities, customization options, ease of use, and the ability to facilitate human and LLM collaboration.

              @@ -2243,8 +2244,14 @@

              +

              4.10. Conclusion

              +

              Language models have fundamentally transformed how software is developed and evaluated. Unlike conventional systems that produce predictable outputs, LLMs generate varied, probabilistic responses that defy traditional testing approaches. While developers accustomed to deterministic systems may find this shift challenging, continuing to rely on legacy testing methods is unsustainable. These frameworks were not designed to handle the inherent variability of LLM outputs and will ultimately prove inadequate.

              +

              Success requires embracing this new paradigm by implementing comprehensive evaluation strategies early - this is the new Product Requirements Document (PRD) - and cultivating an organizational mindset focused on iteration, experimentation and growth.

              +

              The shift from traditional software testing to LLM evaluation is not just a change in tools but a transformation in mindset. Those who recognize and adapt to this shift will lead the way in harnessing the power of LLMs. However, the cost of inaction is not just technological stagnation, but potential business failure.

              +
              -

              4.9. References

              +

              4.11. References

              [ALB+24] diff --git a/tamingllms/_build/html/searchindex.js b/tamingllms/_build/html/searchindex.js index 785edaf..1dc53ac 100644 --- a/tamingllms/_build/html/searchindex.js +++ b/tamingllms/_build/html/searchindex.js @@ -1 +1 @@ -Search.setIndex({"docnames": ["markdown/intro", "markdown/toc", "notebooks/evals", "notebooks/output_size_limit", "notebooks/structured_output"], "filenames": ["markdown/intro.md", "markdown/toc.md", "notebooks/evals.ipynb", "notebooks/output_size_limit.ipynb", "notebooks/structured_output.ipynb"], "titles": ["1. Introduction", "Taming LLMs", "4. The Evals Gap", "2. Output Size Limitations", "3. Wrestling with Structured Output"], "terms": {"am": 0, "alwai": [0, 2, 4], "do": [0, 2, 3, 4], "which": [0, 2, 3, 4], "cannot": [0, 2], "order": [0, 2, 4], "mai": [0, 2, 3, 4], "learn": [0, 2], "how": [0, 2, 3, 4], "pablo": [0, 2], "picasso": 0, "In": [0, 2, 3, 4], "recent": [0, 2, 4], "year": [0, 1, 2, 3, 4], "larg": [0, 1, 2, 3, 4], "languag": [0, 1, 2, 3, 4], "model": [0, 1, 4], "llm": [0, 3, 4], "have": [0, 2, 3, 4], "emerg": [0, 1, 4], "transform": [0, 2, 4], "forc": [0, 2, 4], "technologi": [0, 2, 3, 4], "promis": [0, 2], "revolution": 0, "build": [0, 1, 2, 3, 4], "product": [0, 1, 2, 4], "interact": [0, 2, 3, 4], "comput": [0, 2, 3, 4], "from": [0, 2, 3, 4], "chatgpt": [0, 4], "github": [0, 1, 2, 4], "copilot": 0, "claud": [0, 2, 3], "artifact": 0, "system": [0, 2, 3, 4], "captur": [0, 2], "public": [0, 2], "imagin": 0, "spark": 0, "gold": [0, 2], "rush": 0, "ai": [0, 2, 4], "power": [0, 1, 2, 3, 4], "applic": [0, 1, 3, 4], "howev": [0, 2, 3, 4], "beneath": 0, "surfac": [0, 2], "technolog": [0, 2], "revolut": 0, "li": [0, 2], "complex": [0, 2, 3, 4], "landscap": [0, 2], "practition": [0, 2], "must": [0, 2, 3], "navig": [0, 1, 2], "focus": [0, 2, 3, 4], "bring": 0, "awar": [0, 2, 3], "limit": [0, 2, 4], "har": [0, 1, 3], "open": [0, 2, 3, 4], "sourc": [0, 2, 4], "solut": [0, 1, 2, 3], "overcom": [0, 3], "them": [0, 2, 3, 4], "robust": [0, 2, 3, 4], "It": [0, 2, 3, 4], "offer": [0, 2, 3, 4], "critic": [0, 1, 2, 3, 4], "implement": [0, 1, 2, 3, 4], "back": [0, 2, 4], "reproduc": [0, 1, 2], "exampl": [0, 1, 2, 4], "while": [0, 1, 2, 3, 4], "mani": [0, 2, 3, 4], "resourc": [0, 2, 3], "cover": [0, 2, 3], "capabl": [0, 1, 2, 3, 4], "specif": [0, 1, 2, 3], "hidden": 0, "pitfal": 0, "engin": [0, 1, 2, 4], "technic": [0, 1, 2, 3, 4], "manag": [0, 1, 2, 3, 4], "face": [0, 2], "when": [0, 1, 2, 3, 4], "comprehens": [0, 1, 2, 3, 4], "guid": [0, 2, 4], "leverag": [0, 2, 3, 4], "battl": [0, 1], "test": [0, 1, 4], "tool": [0, 3], "throughout": [0, 2, 3, 4], "tackl": [0, 2], "follow": [0, 2, 3, 4], "non": [0, 1, 4], "exhaust": 0, "list": [0, 2, 3, 4], "structur": [0, 2, 3], "un": 0, "reliabl": [0, 2, 4], "struggl": [0, 2, 4], "maintain": [0, 2, 3, 4], "consist": [0, 2, 3, 4], "output": [0, 2], "format": [0, 2, 3, 4], "complic": 0, "integr": [0, 2, 4], "larger": [0, 2, 3, 4], "make": [0, 2, 3, 4], "error": [0, 2, 4], "handl": [0, 1, 2, 3, 4], "more": [0, 2, 3, 4], "size": [0, 2, 4], "length": [0, 2, 4], "constraint": [0, 1, 2, 3, 4], "strict": [0, 4], "token": [0, 1, 2, 4], "both": [0, 2], "input": [0, 2, 3, 4], "requir": [0, 3, 4], "care": [0, 2, 4], "chunk": [0, 1], "strategi": [0, 1, 2, 3], "long": [0, 1, 2, 4], "form": [0, 1, 2, 4], "effect": [0, 2, 3, 4], "tradit": 0, "softwar": [0, 4], "methodologi": [0, 2, 4], "break": [0, 2, 3], "down": [0, 2, 3], "deal": 0, "determinist": [0, 1, 4], "gener": [0, 1, 4], "new": [0, 2, 3, 4], "hallucin": [0, 2, 4], "These": [0, 2, 3, 4], "can": [0, 2, 3, 4], "plausibl": 0, "sound": 0, "entir": [0, 2, 3, 4], "fabric": [0, 2], "inform": [0, 2, 3, 4], "creat": [0, 2, 3, 4], "signific": [0, 2, 3, 4], "risk": [0, 2, 3], "safeti": [0, 2, 4], "secur": [0, 2, 3, 4], "harm": [0, 2], "bias": [0, 2, 4], "inappropri": 0, "safeguard": [0, 2], "monitor": [0, 1, 2], "ensur": [0, 2, 3, 4], "safe": [0, 2, 4], "deploy": [0, 1, 2, 4], "cost": [0, 2, 4], "optim": [0, 1, 2, 3], "The": [0, 3, 4], "financi": [0, 2, 3, 4], "oper": [0, 2, 3, 4], "base": [0, 1, 4], "quickli": [0, 3], "becom": [0, 2, 4], "prohibit": [0, 2], "without": [0, 2, 3, 4], "observ": [0, 2, 4], "vendor": [0, 1, 2], "lock": [0, 1], "cloud": [0, 2, 4], "provid": [0, 2, 3], "depend": [0, 2, 4], "through": [0, 1, 2, 3, 4], "proprietari": [0, 4], "infrastructur": 0, "difficult": [0, 2], "switch": 0, "self": [0, 1, 2], "host": [0, 1, 2], "take": [0, 1, 2, 3, 4], "hand": [0, 3, 4], "concret": [0, 1], "you": [0, 2, 3, 4], "run": [0, 2, 4], "modifi": [0, 2], "real": [0, 2, 3, 4], "world": [0, 2, 4], "scenario": [0, 2, 4], "best": [0, 1, 2], "techniqu": [0, 1, 2, 3], "pattern": [0, 1, 2, 4], "anti": [0, 2], "look": [0, 1, 2], "our": [0, 2, 3, 4], "goal": [0, 2, 3], "discourag": 0, "us": [0, 3, 4], "enabl": [0, 2, 3, 4], "By": [0, 1, 2, 3, 4], "understand": [0, 1, 2, 3, 4], "upfront": [0, 1], "better": [0, 1, 2, 3], "equip": [0, 1, 2], "avoid": [0, 2, 4], "current": [0, 1, 2, 3, 4], "discours": [0, 1], "around": [0, 1, 2, 3, 4], "tend": [0, 1, 2], "toward": [0, 2, 4], "extrem": [0, 2], "either": [0, 2, 3], "uncrit": 0, "enthusiasm": 0, "wholesal": [0, 2], "dismiss": 0, "differ": [0, 2, 3, 4], "focu": [0, 1, 2, 3, 4], "rather": [0, 2], "than": [0, 2], "theoret": 0, "examin": [0, 2, 3, 4], "first": [0, 2, 3, 4], "everi": [0, 2], "concept": [0, 2], "illustr": [0, 2, 3, 4], "execut": [0, 2], "immedi": [0, 2], "analysi": [0, 1, 2, 3], "balanc": [0, 2, 3, 4], "help": [0, 2, 3, 4], "reader": [0, 1], "decis": [0, 2, 4], "intend": [0, 2], "develop": [0, 2, 3, 4], "step": [0, 1, 2, 4], "insight": [0, 2, 3, 4], "along": [0, 2], "guidanc": [0, 4], "framework": [0, 2], "could": [0, 2, 3, 4], "derail": 0, "project": [0, 2], "earli": [0, 2, 4], "befor": [0, 2, 4], "thei": [0, 2, 3, 4], "costli": [0, 2], "problem": [0, 1], "too": [0, 2, 3], "late": 0, "lifecycl": 0, "design": [0, 1, 3, 4], "lead": [0, 2, 3, 4], "genai": 0, "initi": [0, 2, 3, 4], "leader": [0, 2], "architectur": [0, 2, 3, 4], "advoc": 0, "anyon": 0, "seek": [0, 2], "work": [0, 1, 2, 3, 4], "typic": [0, 2, 3, 4], "job": [0, 2], "role": [0, 2, 3, 4], "platform": [0, 2, 3, 4], "backend": [0, 2], "exist": [0, 2], "ml": 0, "transit": [0, 2, 3, 4], "overse": 0, "motiv": [0, 2, 4], "need": [0, 2, 3], "readi": [0, 2], "desir": [0, 2, 4], "perform": [0, 1, 2, 3, 4], "after": [0, 2, 3, 4], "read": [0, 2, 3, 4], "implic": [0, 1, 2], "experi": [0, 2, 3, 4], "recommend": [0, 2, 3, 4], "abl": [0, 2, 3, 4], "deploi": [0, 2, 3], "proper": [0, 4], "realist": 0, "effort": [0, 2, 4], "estim": [0, 2], "impact": [0, 2, 3, 4], "timelin": 0, "To": [0, 2, 3, 4], "most": [0, 2, 3, 4], "should": [0, 2, 3, 4], "basic": [0, 2, 3], "program": [0, 2], "knowledg": [0, 2], "introductori": [0, 1], "langchain": [0, 1, 2, 3], "e": [0, 2, 3, 4], "g": [0, 2, 3, 4], "chat": [0, 2, 3, 4], "prompt": [0, 1, 2], "templat": [0, 1, 2], "access": [0, 2, 3, 4], "openai": [0, 2, 4], "anthrop": [0, 4], "similar": [0, 2, 4], "grade": [0, 2], "dive": 0, "here": [0, 2, 3, 4], "get": [0, 2, 3, 4], "start": [0, 2, 4], "activ": [0, 2], "virtual": [0, 2], "m": [0, 2, 4], "venv": 0, "env": [0, 2, 3, 4], "bin": 0, "On": [0, 2, 4], "window": [0, 1, 2], "script": 0, "instal": [0, 2, 4], "packag": [0, 2, 4], "pip": [0, 2, 4], "r": [0, 2, 3, 4], "txt": [0, 2, 3, 4], "file": [0, 2, 3, 4], "root": 0, "directori": [0, 2], "add": [0, 2, 3], "other": [0, 2, 3, 4], "sensit": [0, 2], "openai_api_kei": 0, "your_openai_api_key_her": 0, "never": [0, 4], "share": [0, 2, 4], "commit": [0, 2], "version": [0, 2, 4], "control": [0, 2, 4], "contain": [0, 2, 3, 4], "kept": [0, 2], "privat": [0, 2], "clone": 0, "companion": 0, "git": 0, "http": [0, 1, 2, 3, 4], "com": [0, 1, 2, 3, 4], "souzatharsi": [0, 1], "tamingllm": [0, 1], "cd": 0, "If": [0, 2, 4], "encount": [0, 1, 2], "rate": [0, 2], "consid": [0, 2, 3, 4], "smaller": [0, 2, 3, 4], "retri": [0, 4], "logic": [0, 2, 3], "conflict": [0, 2], "try": [0, 2, 4], "fresh": 0, "like": [0, 2, 3, 4], "poetri": 0, "check": [0, 2, 4], "page": [0, 2], "known": [0, 2, 4], "now": [0, 2, 3, 4], "let": [0, 2, 3, 4], "begin": [0, 2, 4], "explor": [0, 2, 4], "dr": 0, "tharsi": [0, 1], "souza": [0, 1], "scientist": 0, "special": [0, 2, 4], "he": [0, 2], "lectur": 0, "columbia": 0, "univers": [0, 2], "master": [0, 4], "scienc": [0, 2], "appli": [0, 2, 3, 4], "analyt": 0, "head": [0, 2, 3], "equiti": [0, 2], "citadel": 0, "former": [0, 2], "senior": [0, 2], "vp": 0, "two": [0, 2, 3, 4], "sigma": 0, "invest": [0, 2, 4], "With": [0, 2], "over": [0, 1, 2, 3, 4], "15": [0, 2, 4], "deliv": [0, 2], "across": [0, 2, 4], "startup": 0, "fortun": 0, "500": [0, 2], "compani": [0, 2, 3, 4], "global": [0, 2], "also": [0, 2, 3, 4], "an": [0, 1, 2, 3, 4], "numer": [0, 2], "scholarli": 0, "frequent": [0, 2, 4], "speaker": [0, 2], "academ": [0, 2], "busi": [0, 2], "confer": [0, 4], "ground": [0, 1, 2], "background": [0, 2, 3], "draw": [0, 2, 4], "scale": [0, 2, 4], "stage": [0, 4], "major": [0, 2, 4], "institut": [0, 2], "well": [0, 2, 4], "advis": 0, "profit": [0, 2, 3, 4], "organ": [0, 2, 3], "contribut": [0, 2, 3], "uniqu": [0, 2], "bridg": 0, "gap": 0, "between": [0, 2, 3, 4], "potenti": [0, 2, 3, 4], "next": [0, 2, 4], "hold": [0, 2], "ph": 0, "d": [0, 2, 4], "ucl": 0, "london": 0, "phil": 0, "sc": 0, "b": [0, 2, 4], "abstract": [1, 2, 4], "heavili": [1, 2, 4], "gloss": 1, "fundament": [1, 2, 4], "challeng": [1, 2, 3, 4], "convers": [1, 2, 3, 4], "thi": [1, 2, 3, 4], "book": [1, 2], "kei": [1, 4], "python": [1, 2, 3, 4], "proven": 1, "yet": [1, 2, 3], "i": [1, 2, 3, 4], "unstructur": [1, 4], "context": [1, 2, 3, 4], "code": [1, 2, 4], "sidestep": 1, "inher": [1, 2, 3, 4], "core": [1, 2], "we": [1, 2, 3, 4], "ll": [1, 2], "address": [1, 2, 3, 4], "approach": [1, 2, 3, 4], "note": [1, 2, 3, 4], "perspect": 1, "who": [1, 2, 3, 4], "For": [1, 2, 3, 4], "outcom": [1, 2, 4], "prerequisit": 1, "set": [1, 2, 3, 4], "up": [1, 2, 3, 4], "your": [1, 2, 3, 4], "environ": [1, 2, 3, 4], "setup": [1, 2, 4], "api": [1, 2], "configur": [1, 2], "repositori": [1, 2], "troubleshoot": 1, "common": [1, 2, 3, 4], "issu": [1, 2, 3, 4], "about": [1, 2, 3, 4], "author": [1, 2, 4], "": [1, 2, 3, 4], "statement": 1, "One": [1, 2], "shot": [1, 2], "json": [1, 2, 3], "mode": 1, "outlin": [1, 2], "multipl": [1, 2, 3, 4], "choic": [1, 2, 4], "pydant": [1, 2, 4], "discuss": [1, 2], "compar": [1, 2, 3], "research": [1, 2, 3], "ongo": [1, 2], "debat": 1, "conclus": [1, 2], "acknowledg": [1, 2], "refer": 1, "content": 1, "what": [1, 2, 4], "ar": [1, 2, 4], "contextu": [1, 2], "link": [1, 2], "write": [1, 2, 4], "construct": [1, 2, 4], "dynam": [1, 2], "paramet": [1, 2, 4], "report": [1, 2, 4], "usag": [1, 2, 4], "futur": [1, 2], "consider": [1, 4], "machin": [1, 4], "temperatur": [1, 3, 4], "sampl": [1, 3, 4], "spectrum": 1, "properti": 1, "conceptu": [1, 4], "overview": [1, 4], "compon": [1, 2], "metric": 1, "evalu": [1, 3, 4], "human": [1, 3, 4], "benchmark": 1, "leaderboard": 1, "type": [1, 2, 3, 4], "detect": [1, 2, 4], "retriev": [1, 2], "augment": [1, 2], "rag": 1, "select": [1, 2], "index": [1, 2, 3, 4], "vector": 1, "store": [1, 2, 3], "method": [1, 2, 3, 4], "pipelin": [1, 2, 4], "valid": [1, 2, 4], "guard": 1, "filter": [1, 2, 4], "sanit": 1, "alert": 1, "cach": [1, 2], "invalid": [1, 4], "predict": [1, 2, 4], "llama": [1, 2, 4], "llamafil": 1, "ollama": 1, "migrat": 1, "commun": [1, 2, 4], "misc": 1, "tharsistpsouza2024tamingllm": 1, "t": [1, 2, 3, 4], "p": [1, 2, 4], "titl": [1, 2], "2024": [1, 2, 3, 4], "journal": [1, 2, 4], "url": [1, 2, 4], "doesn": [2, 3, 4], "matter": 2, "beauti": 2, "theori": 2, "smart": 2, "agre": 2, "wrong": 2, "richard": 2, "feynman": 2, "natur": [2, 3, 4], "unlik": 2, "where": [2, 3, 4], "same": [2, 3, 4], "produc": [2, 4], "novel": 2, "text": [2, 3, 4], "train": [2, 4], "data": [2, 3, 4], "respons": [2, 3, 4], "each": [2, 3, 4], "time": [2, 3, 4], "re": [2, 3, 4], "queri": 2, "even": [2, 3, 4], "ident": 2, "behavior": 2, "strength": 2, "ask": [2, 4], "question": [2, 4], "isn": 2, "bug": 2, "featur": [2, 4], "random": [2, 4], "allow": [2, 3, 4], "creativ": [2, 4], "divers": [2, 3, 4], "testabl": 2, "servic": [2, 3, 4], "advic": 2, "mean": [2, 3, 4], "yield": 2, "exceedingli": 2, "regulatori": 2, "complianc": [2, 4], "guarante": [2, 4], "user": [2, 3], "trust": [2, 4], "affect": 2, "inconsist": [2, 4], "primari": 2, "determin": [2, 3, 4], "come": [2, 3, 4], "dure": [2, 4], "calcul": 2, "probabl": [2, 4], "distribut": [2, 4], "nucleu": 2, "holtzman": 2, "et": [2, 4], "al": [2, 4], "2020": 2, "top": [2, 4], "k": [2, 3, 4], "coher": [2, 3], "0": [2, 3, 4], "repetit": [2, 3, 4], "1": [2, 4], "increas": [2, 3, 4], "incoher": 2, "A": [2, 3, 4], "repres": [2, 4], "unscal": 2, "score": [2, 4], "vocabulari": [2, 4], "decreas": 2, "closer": 2, "sharpen": 2, "so": [2, 4], "higher": 2, "uniform": 2, "raschka": 2, "simpl": [2, 3, 4], "singl": [2, 3, 4], "summari": [2, 4], "dramat": [2, 4], "alter": 2, "wai": [2, 3, 4], "systemat": [2, 4], "assess": [2, 3], "At": [2, 4], "rigid": 2, "vari": 2, "less": 2, "2": [2, 4], "wildli": 2, "often": [2, 3, 4], "inadequ": 2, "dotenv": [2, 3, 4], "import": [2, 3, 4], "load_dotenv": [2, 3, 4], "o": [2, 3, 4], "load": [2, 3, 4], "variabl": [2, 3, 4], "panda": 2, "pd": 2, "def": [2, 3, 4], "generate_respons": 2, "model_nam": [2, 3], "str": [2, 3, 4], "float": [2, 3], "attempt": [2, 3], "int": [2, 3], "3": [2, 4], "datafram": 2, "demonstr": [2, 3, 4], "client": [2, 4], "result": [2, 3, 4], "temp": 2, "rang": [2, 3, 4], "complet": [2, 3, 4], "messag": [2, 4], "max_token": 2, "50": 2, "append": [2, 3, 4], "displai": [2, 4], "group": [2, 3], "df_result": 2, "print": [2, 3, 4], "f": [2, 3, 4], "ntemperatur": 2, "40": 2, "temp_respons": 2, "_": [2, 4], "row": 2, "iterrow": 2, "return": [2, 3, 4], "max_length": [2, 4], "10000": [2, 3, 4], "appl": [2, 3, 4], "sec_fil": [2, 4], "unit": [2, 3, 4], "state": [2, 3, 4], "nsecur": 2, "AND": [2, 4], "exchang": [2, 3, 4], "commiss": [2, 3, 4], "nwashington": 2, "c": [2, 4], "20549": 2, "n": [2, 3, 4], "nform": 2, "10": [2, 3, 4], "mark": 2, "annual": 2, "pursuant": 2, "TO": 2, "section": [2, 3, 4], "13": 2, "OR": 2, "OF": 2, "THE": 2, "act": 2, "1934": 2, "nfor": 2, "fiscal": [2, 3], "end": [2, 3, 4], "septemb": [2, 3], "28": [2, 3], "nor": 2, "period": [2, 3], "ncommiss": 2, "number": [2, 3, 4], "001": 2, "36743": 2, "ng66145g66i43": 2, "jpg": 2, "nappl": 2, "inc": [2, 3, 4], "exact": 2, "name": [2, 3, 4], "registr": 2, "specifi": [2, 3, 4], "its": [2, 3, 4], "charter": 2, "ncalifornia": 2, "t94": 2, "2404110": 2, "jurisdict": 2, "nof": 2, "incorpor": 2, "employ": 2, "identif": 2, "No": [2, 4], "none": 2, "park": 2, "ncupertino": 2, "california": [2, 4], "n95014": 2, "princip": 2, "offic": 2, "zip": 2, "408": 2, "996": 2, "1010": 2, "telephon": 2, "includ": [2, 3, 4], "area": [2, 4], "regist": 2, "12": [2, 3], "ntitl": 2, "class": [2, 3, 4], "ttrade": 2, "symbol": 2, "tname": 2, "ncommon": 2, "stock": [2, 4], "00001": 2, "par": 2, "valu": [2, 3, 4], "per": [2, 3], "naapl": 2, "tthe": 2, "nasdaq": [2, 4], "market": [2, 3, 4], "llc": [2, 4], "n0": 2, "000": [2, 4], "due": [2, 3], "2025": 2, "875": 2, "n1": 2, "625": 2, "2026": 2, "n2": 2, "2027": 2, "375": 2, "2029": 2, "n3": 2, "050": 2, "2031": 2, "600": 2, "2042": 2, "nindic": 2, "season": 2, "issuer": 2, "defin": [2, 3, 4], "rule": [2, 3, 4], "405": 2, "nye": 2, "whether": [2, 3, 4], "ha": [2, 4], "all": [2, 3, 4], "preced": 2, "month": 2, "shorter": 2, "wa": [2, 4], "been": 2, "subject": 2, "past": 2, "90": 2, "dai": [2, 4], "submit": 2, "electron": 2, "regul": [2, 4], "232": 2, "chapter": 2, "acceler": 2, "filer": 2, "growth": 2, "see": [2, 4], "definit": [2, 4], "12b": 2, "nlarg": 2, "tacceler": 2, "nnon": 2, "tsmaller": 2, "nemerg": 2, "nif": 2, "indic": [2, 4], "elect": 2, "extend": [2, 4], "compli": [2, 4], "ani": [2, 3, 4], "revis": 2, "account": 2, "standard": 2, "attest": 2, "intern": 2, "under": [2, 4], "404": 2, "sarban": 2, "oxlei": 2, "u": [2, 4], "7262": 2, "firm": 2, "prepar": [2, 3], "audit": 2, "reflect": 2, "correct": [2, 4], "previous": [2, 3, 4], "those": [2, 3, 4], "restat": 2, "recoveri": 2, "incent": 2, "compens": 2, "receiv": [2, 3, 4], "relev": 2, "240": 2, "10d": 2, "shell": 2, "nthe": 2, "aggreg": 2, "vote": 2, "held": [2, 4], "affili": [2, 4], "march": [2, 4], "29": [2, 4], "last": [2, 3, 4], "second": [2, 3], "quarter": 2, "approxim": [2, 4], "628": [2, 4], "553": [2, 4], "sole": 2, "purpos": [2, 4], "disclosur": 2, "director": 2, "date": [2, 4], "exclud": 2, "becaus": 2, "person": [2, 4], "deem": 2, "necessarili": 2, "n15": 2, "115": [2, 4], "823": [2, 4], "were": [2, 4], "outstand": [2, 4], "octob": [2, 4], "18": [2, 4], "ndocument": 2, "BY": 2, "nportion": 2, "proxi": 2, "relat": 2, "meet": [2, 4], "sharehold": 2, "part": [2, 3, 4], "iii": 2, "within": [2, 3, 4], "120": 2, "ntabl": 2, "npage": 2, "npart": 2, "nitem": 2, "nbusi": 2, "1a": 2, "nrisk": 2, "factor": [2, 3, 4], "n5": 2, "1b": 2, "nunresolv": 2, "staff": 2, "comment": 2, "n17": 2, "1c": 2, "ncybersecur": 2, "nproperti": 2, "n18": 2, "nlegal": 2, "proceed": 2, "4": [2, 4], "nmine": 2, "ii": [2, 4], "5": [2, 3, 4], "nmarket": 2, "stockhold": 2, "purchas": 2, "n19": 2, "6": [2, 3, 4], "reserv": 2, "n20": 2, "7": [2, 3], "nmanag": 2, "condit": 2, "n21": 2, "7a": 2, "nquantit": 2, "qualit": 2, "n27": 2, "8": [2, 3], "nfinanci": 2, "supplementari": 2, "n28": 2, "9": 2, "nchang": 2, "disagr": 2, "n51": 2, "9a": 2, "ncontrol": 2, "procedur": 2, "9b": 2, "nother": 2, "n52": 2, "9c": 2, "ndisclosur": 2, "regard": 2, "foreign": 2, "prevent": [2, 4], "inspect": 2, "ndirector": 2, "corpor": 2, "govern": 2, "11": 2, "nexecut": 2, "ownership": 2, "certain": [2, 3, 4], "benefici": 2, "owner": 2, "ncertain": 2, "relationship": 2, "transact": 2, "independ": [2, 4], "14": [2, 4], "nprincip": 2, "fee": 2, "iv": 2, "nexhibit": 2, "schedul": 2, "n53": 2, "16": 2, "n56": 2, "nthi": 2, "forward": 2, "litig": 2, "reform": 2, "1995": 2, "involv": [2, 4], "uncertainti": 2, "locat": 2, "item": 2, "expect": [2, 3, 4], "event": 2, "assumpt": 2, "doe": [2, 3, 4], "directli": [2, 4], "histor": 2, "fact": 2, "macroeconom": 2, "identifi": [2, 3, 4], "word": [2, 3, 4], "anticip": 2, "believ": [2, 4], "plan": [2, 4], "would": [2, 3, 4], "term": [2, 3], "actual": [2, 3, 4], "significantli": [2, 3], "might": [2, 3, 4], "caus": 2, "assum": [2, 3], "oblig": [2, 3], "updat": [2, 3, 4], "reason": [2, 3, 4], "except": [2, 4], "law": 2, "nunless": 2, "otherwis": 2, "present": [2, 3, 4], "herein": 2, "calendar": 2, "particular": [2, 4], "associ": [2, 3, 4], "collect": [2, 3], "wholli": 2, "own": [2, 3], "subsidiari": 2, "unless": 2, "ncompani": 2, "manufactur": 2, "smartphon": 2, "tablet": 2, "wearabl": [2, 4], "accessori": 2, "sell": 2, "varieti": 2, "52": 2, "53": 2, "week": 2, "saturdai": 2, "nproduct": 2, "niphon": 2, "line": 2, "io": [2, 4], "iphon": [2, 4], "pro": [2, 3], "se": 2, "nmac": 2, "maco": 2, "mac": [2, 4], "laptop": 2, "macbook": 2, "air": 2, "desktop": 2, "imac": 2, "mini": [2, 3, 4], "studio": 2, "nipad": 2, "multipurpos": 2, "ipado": 2, "ipad": [2, 4], "nwearabl": 2, "home": 2, "smartwatch": 2, "wireless": 2, "headphon": 2, "spatial": 2, "watcho": 2, "watch": 2, "ultra": 2, "seri": 2, "airpod": 2, "max": 2, "beat": 2, "vision": 2, "visiono": 2, "nhome": 2, "tv": 2, "media": 2, "stream": [2, 4], "game": 2, "devic": [2, 4], "tvo": 2, "homepod": 2, "high": [2, 3, 4], "fidel": [2, 4], "naccessori": 2, "brand": 2, "third": 2, "parti": 2, "nservic": 2, "nadvertis": 2, "advertis": 2, "licens": 2, "arrang": 2, "napplecar": 2, "portfolio": [2, 4], "support": [2, 4], "applecar": 2, "prioriti": 2, "network": [2, 4], "repair": 2, "replac": 2, "case": [2, 3, 4], "addit": [2, 3, 4], "coverag": 2, "instanc": [2, 3], "accident": 2, "damag": 2, "theft": 2, "loss": 2, "countri": 2, "ncloud": 2, "keep": [2, 3], "custom": 2, "avail": [2, 3, 4], "ndigit": 2, "variou": [2, 3, 4], "app": 2, "discov": 2, "download": 2, "digit": 2, "music": 2, "video": 2, "podcast": 2, "subscript": 2, "arcad": 2, "fit": [2, 3, 4], "sm": 2, "curat": 2, "listen": 2, "demand": [2, 4], "radio": 2, "station": 2, "magazin": 2, "exclus": 2, "origin": [2, 3, 4], "live": 2, "sport": 2, "npayment": 2, "payment": 2, "card": 2, "co": 2, "credit": 2, "pai": 2, "cashless": 2, "nsegment": 2, "primarili": 2, "geograph": 2, "basi": 2, "segment": [2, 3, 4], "america": 2, "europ": 2, "greater": 2, "china": 2, "japan": 2, "rest": 2, "asia": 2, "pacif": 2, "north": 2, "south": 2, "european": 2, "india": 2, "middl": 2, "east": 2, "africa": 2, "mainland": 2, "hong": 2, "kong": 2, "taiwan": 2, "australia": 2, "asian": 2, "although": 2, "hardwar": 2, "one": [2, 3, 4], "separ": [2, 3], "align": [2, 3, 4], "partner": 2, "region": 2, "consum": [2, 4], "small": [2, 4], "mid": [2, 3], "educ": [2, 3], "enterpris": [2, 4], "resel": 2, "retail": 2, "onlin": 2, "direct": 2, "sale": 2, "emploi": [2, 4], "indirect": 2, "channel": 2, "cellular": 2, "carrier": 2, "net": [2, 4], "38": 2, "62": 2, "respect": 2, "total": [2, 3, 4], "ncompetit": 2, "highli": [2, 4], "competit": 2, "character": 2, "aggress": 2, "price": 2, "downward": 2, "pressur": 2, "gross": 2, "margin": [2, 4], "introduct": [2, 3], "short": [2, 3, 4], "life": 2, "cycl": 2, "evolv": [2, 3], "industri": [2, 4], "continu": [2, 3, 4], "improv": [2, 3, 4], "characterist": 2, "rapid": 2, "adopt": [2, 4], "advanc": [2, 3, 4], "competitor": 2, "compet": 2, "veri": 2, "low": [2, 4], "imit": 2, "infring": 2, "intellectu": 2, "abil": [2, 4], "successfulli": [2, 4], "innov": [2, 3], "marketplac": 2, "nearli": 2, "rel": 2, "qualiti": [2, 3, 4], "strong": [2, 4], "ecosystem": 2, "reput": 2, "expand": 2, "opportun": 2, "substanti": 2, "establish": 2, "some": [2, 3, 4], "broader": 2, "lower": [2, 4], "particularli": [2, 3, 4], "intens": [2, 4], "cut": [2, 3], "littl": 2, "free": 2, "illegitim": 2, "obtain": [2, 4], "collabor": 2, "nsuppli": 2, "nalthough": 2, "essenti": [2, 3, 4], "particip": 2, "therefor": 2, "wide": [2, 3, 4], "shortag": 2, "commod": 2, "fluctuat": 2, "commonli": 2, "introduc": [2, 3, 4], "util": [2, 3], "onli": [2, 3, 4], "capac": 2, "until": [2, 4], "supplier": 2, "matur": 2, "accept": 2, "decid": [2, 3], "concentr": 2, "instead": [2, 3, 4], "enter": 2, "agreement": 2, "suppli": [2, 4], "renew": 2, "nresearch": 2, "nbecaus": 2, "upon": [2, 3], "flow": [2, 3], "enhanc": [2, 3, 4], "acquisit": 2, "nintellectu": 2, "broad": [2, 4], "right": 2, "aspect": [2, 3, 4], "patent": 2, "copyright": 2, "trademark": 2, "trade": [2, 4], "secret": 2, "differenti": 2, "success": [2, 4], "reli": 2, "skill": 2, "personnel": 2, "regularli": 2, "protect": 2, "aris": 2, "pursu": 2, "thousand": 2, "accumul": 2, "durat": 2, "adequ": 2, "nin": 2, "necessari": [2, 3], "process": [2, 3, 4], "commerci": [2, 4], "experienc": 2, "holidai": 2, "addition": 2, "expens": 2, "fill": 2, "inventori": 2, "launch": 2, "older": 2, "declin": 2, "newer": 2, "distributor": 2, "nhuman": 2, "capit": [2, 3, 4], "peopl": 2, "plai": [2, 4], "strive": 2, "attract": 2, "retain": [2, 3], "talent": 2, "inclus": [2, 3, 4], "team": [2, 4], "member": 2, "As": [2, 3, 4], "had": 2, "164": 2, "full": [2, 3, 4], "equival": 2, "employe": 2, "ncompens": 2, "benefit": [2, 4], "equit": 2, "recogn": 2, "thrive": [2, 4], "succe": 2, "profession": [2, 4], "health": 2, "awai": 2, "ngrowth": 2, "achiev": [2, 4], "career": 2, "leadership": 2, "influenc": [2, 4], "cultur": 2, "advantag": [2, 3, 4], "being": 2, "nworkplac": 2, "practic": [2, 3], "polici": 2, "equal": 2, "workplac": 2, "harass": 2, "discrimin": 2, "ninclus": 2, "sustain": 2, "workforc": 2, "serv": [2, 3, 4], "represent": [2, 3], "level": [2, 3, 4], "foster": [2, 4], "nengag": 2, "honest": 2, "among": 2, "everyon": 2, "grow": [2, 4], "encourag": [2, 4], "feedback": [2, 4], "concern": 2, "conduct": 2, "survei": [2, 4], "gaug": 2, "sentiment": [2, 4], "nhealth": 2, "everywher": 2, "measur": 2, "mitig": [2, 3, 4], "possibl": [2, 4], "hazard": 2, "crisi": 2, "put": 2, "place": [2, 4], "visitor": 2, "navail": 2, "quarterli": 2, "q": 2, "amend": 2, "sec": [2, 3, 4], "Such": 2, "charg": 2, "investor": [2, 4], "default": [2, 4], "aspx": 2, "websit": 2, "www": 2, "press": 2, "releas": [2, 4], "environment": 2, "social": 2, "detail": [2, 3, 4], "referenc": 2, "further": [2, 3, 4], "inact": 2, "textual": 2, "unknown": 2, "describ": 2, "below": [2, 3, 4], "materi": [2, 4], "advers": 2, "trend": [2, 4], "conjunct": 2, "consolid": 2, "accompani": 2, "nmacroeconom": 2, "econom": 2, "outsid": 2, "chain": [2, 3], "facil": 2, "assembli": 2, "site": 2, "nadvers": 2, "slow": 2, "recess": 2, "unemploy": 2, "inflat": 2, "tighter": 2, "interest": [2, 3, 4], "currenc": 2, "confid": [2, 4], "spend": 2, "chang": 2, "monetari": 2, "volatil": 2, "incom": 2, "asset": 2, "contract": 2, "logist": 2, "instabl": 2, "inabl": 2, "financ": 2, "insolv": 2, "failur": 2, "deriv": 2, "counterparti": 2, "debt": 2, "reduc": [2, 3, 4], "liquid": [2, 3], "fair": 2, "instrument": 2, "polit": 2, "disput": 2, "geopolit": 2, "tension": 2, "terror": 2, "disast": 2, "accid": 2, "interrupt": 2, "npolit": 2, "whole": 2, "outsourc": 2, "korea": 2, "vietnam": 2, "restrict": [2, 4], "tariff": 2, "export": 2, "good": [2, 4], "portion": 2, "revenu": [2, 3, 4], "raw": [2, 4], "go": [2, 3, 4], "action": [2, 3], "restructur": 2, "ceas": 2, "accord": [2, 4], "disrupt": [2, 3], "announc": 2, "notic": [2, 4], "led": [2, 4], "escal": [2, 3], "sever": [2, 3, 4], "nmani": 2, "prone": 2, "earthquak": 2, "climat": 2, "weather": 2, "occur": 2, "fire": 2, "nuclear": 2, "plant": 2, "terrorist": 2, "attack": 2, "hostil": 2, "ransomwar": 2, "cybersecur": 2, "labor": 2, "beyond": 2, "nsuch": 2, "imposs": 2, "delai": 2, "ineffici": 2, "slowdown": 2, "outag": 2, "neg": [2, 4], "seriou": 2, "injuri": 2, "pandem": 2, "covid": 2, "19": 2, "economi": 2, "imposit": 2, "stringent": 2, "travel": 2, "freight": 2, "movement": 2, "ramp": 2, "nfollow": 2, "expenditur": 2, "resum": 2, "lose": 2, "exacerb": 2, "consequ": [2, 4], "insur": 2, "insuffici": 2, "nglobal": 2, "unabl": 2, "There": [2, 3, 4], "assur": 2, "contrast": 2, "minor": 2, "overal": [2, 3, 4], "naddition": 2, "intensifi": 2, "seamlessli": [2, 3], "function": [2, 3, 4], "nto": 2, "remain": [2, 3], "stimul": 2, "ndue": 2, "upgrad": 2, "appropri": [2, 3, 4], "quantiti": 2, "defect": 2, "defici": 2, "supersed": 2, "nsubstanti": 2, "much": 2, "transport": 2, "diminish": 2, "flexibl": [2, 3, 4], "respond": 2, "provis": 2, "reimburs": 2, "warranti": 2, "out": [2, 3, 4], "unanticip": 2, "liabil": 2, "adher": [2, 3, 4], "violat": 2, "final": [2, 3, 4], "finish": 2, "destin": 2, "man": 2, "made": [2, 3, 4], "prepay": 2, "termin": 2, "recover": 2, "exposur": 2, "nfutur": 2, "suffici": [2, 4], "semiconductor": 2, "suffer": 2, "poor": 2, "constrain": [2, 3, 4], "shipment": 2, "altern": [2, 3], "sophist": [2, 3], "unexpectedli": 2, "interfer": 2, "unsaf": 2, "artifici": 2, "intellig": 2, "expos": 2, "inaccur": [2, 4], "fix": [2, 3], "widespread": 2, "vulner": 2, "exploit": 2, "compromis": 2, "claim": 2, "recal": 2, "modif": 2, "off": [2, 3, 4], "intang": 2, "fine": [2, 4], "lost": [2, 3], "cancel": 2, "record": 2, "obsolet": 2, "exce": 2, "realiz": 2, "accru": 2, "excess": 2, "review": [2, 4], "impair": 2, "whenev": 2, "circumst": 2, "amount": [2, 3, 4], "carri": [2, 4], "incur": 2, "given": [2, 3, 4], "unpredict": [2, 4], "pace": 2, "obsolesc": 2, "forecast": 2, "150": 2, "incorrectli": [2, 4], "fulli": [2, 3], "extens": [2, 3, 4], "issuanc": 2, "unknowingli": 2, "notifi": 2, "preclud": 2, "choos": 2, "bui": 2, "percept": 2, "android": 2, "playstat": 2, "nintendo": 2, "xbox": 2, "posit": [2, 3, 4], "inclin": 2, "devot": 2, "compel": [2, 4], "fail": 2, "dissatisfi": 2, "vast": 2, "legal": 2, "storefront": 2, "mechan": [2, 4], "safari": 2, "union": 2, "eu": 2, "dma": 2, "interfac": 2, "reduct": 2, "narrow": 2, "scope": [2, 3], "elimin": 2, "nfailur": 2, "appeal": 2, "subscrib": 2, "nsome": 2, "manner": [2, 3, 4], "nurtur": 2, "distinct": 2, "nmuch": 2, "chief": 2, "especi": [2, 3, 4], "silicon": 2, "vallei": 2, "constantli": 2, "driver": 2, "recruit": 2, "subsidi": 2, "staf": 2, "contractor": 2, "placement": 2, "increment": 2, "weaken": 2, "stop": [2, 3], "telecommun": 2, "war": 2, "virus": 2, "physic": 2, "ins": 2, "incid": 2, "redund": 2, "ineffect": 2, "eventu": 2, "thing": [2, 4], "interf": 2, "imped": 2, "ship": 2, "nloss": 2, "unauthor": 2, "confidenti": 2, "encrypt": 2, "But": [2, 4], "absolut": [2, 4], "malici": 2, "behalf": 2, "gain": 2, "regular": [2, 4], "normal": [2, 4], "investig": 2, "penalti": 2, "judgment": 2, "against": 2, "frequenc": [2, 3], "actor": 2, "circumv": [2, 3], "remov": 2, "obfusc": 2, "forens": 2, "evid": [2, 4], "hinder": [2, 4], "recov": 2, "perpetr": 2, "target": [2, 4], "profil": 2, "authent": 2, "hack": 2, "malfeas": 2, "faulti": 2, "password": 2, "irregular": 2, "fraudul": 2, "induc": 2, "disclos": [2, 3, 4], "usernam": 2, "turn": 2, "multifactor": 2, "unusu": 2, "freez": 2, "suspici": 2, "nwhile": 2, "ninvest": 2, "contempl": 2, "endeavor": 2, "distract": 2, "tangibl": 2, "approv": 2, "oner": 2, "ventur": 2, "riski": 2, "pose": [2, 3, 4], "leas": 2, "unfavor": 2, "arisen": 2, "ordinari": 2, "cours": 2, "resolv": 2, "sometim": [2, 4], "indemnif": 2, "indemnifi": 2, "alleg": 2, "magnitud": 2, "assert": 2, "royalti": 2, "vigor": 2, "defend": 2, "court": 2, "internation": 2, "plaintiff": 2, "injunct": 2, "relief": 2, "nregardless": 2, "merit": 2, "recognit": 2, "settl": 2, "uncertain": 2, "abov": 2, "disgorg": 2, "remedi": 2, "worldwid": 2, "antitrust": 2, "privaci": [2, 4], "local": [2, 3, 4], "bill": 2, "commerc": 2, "internet": 2, "mobil": [2, 4], "televis": 2, "film": 2, "anticorrupt": 2, "cash": [2, 3], "repatri": 2, "monei": 2, "launder": 2, "tax": 2, "wast": 2, "recycl": 2, "ncomplianc": 2, "impos": [2, 4], "interpret": 2, "ethic": 2, "agent": 2, "found": [2, 4], "nregulatori": 2, "satisfi": 2, "ban": 2, "nexpect": 2, "stakehold": 2, "increasingli": [2, 4], "greenhous": 2, "ga": 2, "emiss": 2, "civil": 2, "disagre": 2, "perceiv": 2, "feder": 2, "scrutini": 2, "nfrom": 2, "taken": [2, 4], "engag": [2, 4], "noncompli": 2, "individu": [2, 3], "lawsuit": 2, "monopol": 2, "nfurther": 2, "earn": 2, "googl": [2, 4], "search": 2, "nthere": 2, "connect": [2, 4], "retent": 2, "transfer": 2, "pass": [2, 4], "pend": 2, "inquiri": 2, "government": 2, "entiti": [2, 4], "biometr": 2, "breach": 2, "notif": 2, "permit": [2, 4], "healthcar": 2, "liabl": 2, "investigatori": 2, "cardhold": 2, "compress": [2, 3], "acquir": 2, "shift": 2, "mix": [2, 4], "extent": 2, "unexpect": [2, 4], "dollar": 2, "denomin": 2, "rais": [2, 3], "offset": 2, "strengthen": 2, "nconvers": 2, "therebi": [2, 3], "thu": 2, "option": [2, 3, 4], "hedg": 2, "deterior": 2, "sovereign": 2, "heighten": 2, "worsen": 2, "collater": 2, "bank": 2, "unsecur": 2, "subassembli": 2, "assembl": 2, "few": [2, 3, 4], "legisl": 2, "ireland": 2, "singapor": 2, "organis": 2, "propos": 2, "modern": [2, 3, 4], "minimum": 2, "statutori": 2, "valuat": 2, "defer": 2, "bodi": 2, "likelihood": 2, "adequaci": 2, "ultim": 2, "ow": 2, "ngener": 2, "volum": [2, 3], "unrel": 2, "averag": [2, 4], "repurchas": 2, "point": [2, 3], "dividend": 2, "consumm": 2, "declar": 2, "board": 2, "unresolv": 2, "nnone": 2, "threat": 2, "dedic": [2, 4], "postur": 2, "25": 2, "sinc": [2, 3, 4], "2016": 2, "coordin": 2, "assist": [2, 4], "log": 2, "track": 2, "committe": 2, "oversight": 2, "counsel": 2, "chair": 2, "substanc": 2, "17": 2, "headquart": 2, "cupertino": [2, 4], "land": 2, "center": [2, 4], "suitabl": 2, "formal": [2, 4], "articl": [2, 3], "promot": 2, "conclud": 2, "uninstal": 2, "web": 2, "browser": 2, "screen": 2, "june": 2, "24": [2, 4], "preliminari": 2, "find": [2, 3, 4], "contractu": 2, "desist": 2, "stai": [2, 3], "grant": 2, "ndepart": 2, "justic": 2, "21": 2, "depart": 2, "doj": 2, "district": 2, "attornei": 2, "jersei": 2, "redress": 2, "anticompetit": 2, "nonmonetari": 2, "defens": 2, "itself": 2, "nepic": 2, "epic": 2, "northern": 2, "unfair": 2, "guidelin": 2, "enjoin": 2, "extern": 2, "januari": 2, "motion": 2, "enforc": [2, 4], "oppos": 2, "30": 2, "vacat": 2, "fourth": 2, "did": [2, 4], "mine": 2, "nnot": 2, "aapl": 2, "nholder": 2, "na": 2, "23": 2, "301": 2, "npurchas": 2, "nshare": 2, "three": 2, "million": 2, "nperiod": 2, "ttotal": 2, "taverag": 2, "npaid": 2, "publicli": [2, 4], "nannounc": 2, "napproxim": 2, "That": [2, 4], "Be": 2, "nunder": 2, "njune": 2, "august": 2, "nopen": 2, "negoti": 2, "t35": 2, "697": 2, "t224": 2, "naugust": 2, "31": 2, "t42": 2, "910": 2, "t221": 2, "39": 2, "nseptemb": 2, "t33": 2, "653": 2, "t222": 2, "86": 2, "ntotal": 2, "t112": 2, "260": 2, "t89": 2, "074": 2, "110": 2, "billion": 2, "20": [2, 4], "previou": [2, 3, 4], "2023": [2, 4], "10b5": 2, "graph": 2, "show": [2, 3, 4], "five": 2, "cumul": 2, "reinvest": 2, "dow": 2, "jone": 2, "supersector": 2, "100": [2, 4], "close": 2, "27": 2, "2019": 2, "n2218": 2, "tseptemb": 2, "2021": 2, "2022": 2, "t100": 2, "t207": 2, "t273": 2, "t281": 2, "t322": 2, "t430": 2, "t113": 2, "t156": 2, "t131": 2, "t155": 2, "t210": 2, "ndow": 2, "t146": 2, "t216": 2, "t215": 2, "nfirst": 2, "nsecond": 2, "nthird": 2, "sequoia": 2, "nfourth": 2, "plu": 2, "nfiscal": 2, "six": 2, "realign": 2, "span": 2, "wherea": 2, "indirectli": 2, "tabl": [2, 3, 4], "n2024": 2, "tchang": 2, "t2023": 2, "t2022": 2, "namerica": 2, "t167": 2, "045": 2, "t3": 2, "t162": 2, "560": 2, "t169": 2, "658": 2, "neurop": 2, "t101": 2, "328": 2, "t7": 2, "294": 2, "t95": 2, "118": 2, "ngreater": 2, "t66": 2, "952": 2, "t72": 2, "559": 2, "t74": 2, "200": 2, "njapan": 2, "t25": 2, "052": 2, "t24": 2, "257": 2, "977": 2, "nrest": 2, "t30": 2, "t4": 2, "t29": 2, "615": 2, "t1": 2, "t391": 2, "035": 2, "t2": 2, "t383": 2, "285": 2, "t394": 2, "weak": 2, "renminbi": 2, "yen": [2, 4], "22": 2, "categori": 2, "t201": 2, "183": 2, "t200": 2, "583": 2, "t205": 2, "489": 2, "984": 2, "357": 2, "t40": 2, "177": 2, "t26": 2, "694": 2, "t28": 2, "300": [2, 3], "292": 2, "t37": 2, "005": 2, "t39": 2, "845": 2, "t41": 2, "241": 2, "n96": 2, "169": 2, "t13": 2, "t85": 2, "t9": 2, "t78": 2, "129": 2, "amort": 2, "bundl": 2, "flat": 2, "entri": 2, "partial": [2, 3], "ngross": 2, "percentag": 2, "t109": 2, "633": 2, "t108": 2, "803": 2, "t114": 2, "728": 2, "t71": 2, "t60": 2, "345": 2, "t56": 2, "054": 2, "t180": 2, "683": 2, "148": 2, "t170": 2, "782": 2, "t36": 2, "t73": 2, "t70": 2, "t46": 2, "t44": 2, "t43": 2, "save": [2, 3], "noper": 2, "t31": 2, "370": 2, "t5": 2, "915": 2, "t14": 2, "251": 2, "npercentag": 2, "t8": 2, "nsell": 2, "administr": 2, "097": 2, "932": 2, "094": 2, "t6": 2, "t57": 2, "467": 2, "t54": 2, "847": 2, "t51": 2, "t15": 2, "driven": 2, "headcount": 2, "nprovis": 2, "749": 2, "t16": 2, "741": 2, "t19": 2, "neffect": 2, "nstatutori": 2, "t21": 2, "aid": 2, "nliquid": 2, "unrestrict": 2, "140": 2, "ndebt": 2, "97": 2, "payabl": 2, "promissori": 2, "paper": [2, 4], "nleas": 2, "space": 2, "nmanufactur": 2, "noncancel": 2, "ndeem": 2, "2017": 2, "tcja": 2, "paid": 2, "nstate": 2, "fund": 2, "escrow": 2, "ncapit": 2, "95": 2, "nrecent": 2, "pronounc": 2, "nincom": 2, "decemb": 2, "fasb": 2, "asu": 2, "09": [2, 3], "topic": [2, 3, 4], "740": 2, "reconcili": 2, "reconcil": [2, 4], "quantit": 2, "threshold": 2, "disaggreg": 2, "prospect": 2, "novemb": 2, "07": [2, 3, 4], "280": 2, "maker": 2, "codm": 2, "alloc": 2, "retrospect": 2, "ncritic": 2, "conform": [2, 4], "principl": 2, "gaap": 2, "nuncertain": 2, "domest": 2, "taxat": 2, "adjust": [2, 3, 4], "resolut": 2, "conting": 2, "26": 2, "still": 2, "ninterest": 2, "forth": 2, "hypothet": 2, "nsensit": 2, "nhypothet": 2, "nrate": 2, "npotenti": 2, "n100": 2, "tenor": 2, "ndeclin": 2, "755": 2, "089": 2, "nterm": 2, "nincreas": 2, "t139": 2, "t194": 2, "nforeign": 2, "express": [2, 4], "var": 2, "mont": 2, "carlo": 2, "simul": [2, 4], "maximum": [2, 3], "interv": 2, "538": 2, "669": 2, "underli": [2, 4], "nindex": 2, "tpage": 2, "nconsolid": 2, "n29": 2, "n30": 2, "sheet": 2, "n31": 2, "n32": 2, "n33": 2, "nnote": 2, "n34": 2, "nreport": 2, "n48": 2, "nall": 2, "omit": [2, 4], "submiss": 2, "nyear": 2, "n2023": 2, "n2022": 2, "nnet": 2, "t294": 2, "866": 2, "t298": 2, "085": 2, "t316": 2, "199": 2, "t96": 2, "ncost": 2, "t185": 2, "233": 2, "t189": 2, "282": 2, "471": 2, "119": 2, "855": 2, "t22": 2, "075": 2, "352": 2, "t214": 2, "137": 2, "t223": 2, "546": 2, "t123": 2, "216": 2, "t119": 2, "437": 2, "t269": 2, "565": 2, "334": 2, "485": 2, "736": 2, "103": 2, "t93": 2, "995": 2, "t99": 2, "nearn": 2, "nbasic": 2, "ndilut": 2, "08": [2, 4], "343": 2, "783": 2, "744": 2, "231": 2, "215": 2, "963": 2, "095": 2, "812": 2, "547": 2, "325": 2, "819": 2, "nsee": 2, "translat": 2, "t395": 2, "765": 2, "511": 2, "unreal": 2, "832": 2, "t323": 2, "212": 2, "nadjust": 2, "337": 2, "717": 2, "394": 2, "138": 2, "850": 2, "563": 2, "104": 2, "t204": 2, "t253": 2, "816": 2, "899": 2, "272": 2, "t98": 2, "016": 2, "652": 2, "t88": 2, "531": 2, "nasset": 2, "ncurrent": 2, "ncash": 2, "943": 2, "965": 2, "228": 2, "590": 2, "naccount": 2, "410": 2, "508": 2, "nvendor": 2, "t32": 2, "833": 2, "477": 2, "ninventori": 2, "286": 2, "331": 2, "287": 2, "695": 2, "t152": 2, "987": 2, "t143": 2, "566": 2, "t91": 2, "479": 2, "544": 2, "t45": 2, "680": 2, "715": 2, "834": 2, "t64": 2, "758": 2, "t211": 2, "993": 2, "t209": 2, "017": 2, "t364": 2, "980": 2, "t352": 2, "nliabil": 2, "t68": 2, "960": 2, "t62": 2, "611": 2, "304": 2, "t58": 2, "829": 2, "ndefer": 2, "249": 2, "061": 2, "ncommerci": 2, "967": 2, "985": 2, "t10": 2, "912": 2, "822": 2, "t176": 2, "392": 2, "t145": 2, "308": 2, "750": 2, "281": 2, "888": 2, "t49": 2, "848": 2, "638": 2, "t308": 2, "030": 2, "t290": 2, "ncommit": 2, "nsharehold": 2, "400": 2, "116": 2, "786": 2, "550": 2, "n83": 2, "276": 2, "naccumul": 2, "deficit": 2, "154": 2, "214": 2, "172": 2, "452": 2, "950": 2, "146": 2, "t50": 2, "672": 2, "t63": 2, "090": 2, "nbegin": 2, "849": 2, "365": 2, "423": 2, "346": 2, "175": 2, "withheld": 2, "settlement": 2, "award": 2, "521": 2, "971": 2, "t12": 2, "034": 2, "t11": 2, "nend": 2, "t83": 2, "nretain": 2, "068": 2, "562": 2, "ndividend": 2, "218": 2, "793": 2, "612": 2, "099": 2, "454": 2, "846": 2, "77": 2, "046": 2, "186": 2, "109": 2, "t163": 2, "rsu": 2, "t0": 2, "98": 2, "94": 2, "32": 2, "737": 2, "929": 2, "ndepreci": 2, "445": 2, "519": 2, "688": 2, "038": 2, "266": 2, "227": 2, "006": 2, "788": 2, "356": 2, "271": 2, "520": 2, "618": 2, "484": 2, "731": 2, "684": 2, "499": 2, "020": 2, "889": 2, "448": 2, "552": 2, "031": 2, "t118": 2, "254": 2, "t110": 2, "543": 2, "t122": 2, "151": 2, "48": 2, "656": 2, "513": 2, "76": 2, "923": 2, "nproce": 2, "211": 2, "686": 2, "917": 2, "135": 2, "828": 2, "446": 2, "447": 2, "959": 2, "708": 2, "086": 2, "935": 2, "705": 2, "354": 2, "nfinanc": 2, "441": 2, "431": 2, "223": 2, "234": 2, "025": 2, "841": 2, "nrepurchas": 2, "949": 2, "89": 2, "402": 2, "465": 2, "nrepay": 2, "958": 2, "repay": 2, "978": 2, "955": 2, "361": 2, "581": 2, "160": 2, "121": 2, "983": 2, "108": 2, "488": 2, "794": 2, "760": 2, "nsupplement": 2, "102": 2, "t18": 2, "679": 2, "573": 2, "33": 2, "nbasi": 2, "prior": 2, "reclassifi": 2, "nrevenu": 2, "remit": 2, "straight": 2, "vest": 2, "treat": 2, "sold": 2, "nderiv": 2, "combin": [2, 3, 4], "nonleas": 2, "34": 2, "entitl": 2, "reward": 2, "commenc": 2, "deliveri": 2, "stand": 2, "alon": 2, "ssp": 2, "object": [2, 4], "icloud": 2, "siri": 2, "map": [2, 4], "discount": 2, "lack": [2, 4], "undeliv": 2, "unbil": 2, "accordingli": 2, "n26": 2, "n37": 2, "35": 2, "proport": 2, "moder": 2, "64": 2, "dilut": 2, "nnumer": 2, "ndenomin": 2, "nweight": 2, "312": 2, "316": 2, "856": 2, "antidilut": 2, "tunreal": 2, "ngain": 2, "tfair": 2, "nvalu": 2, "tcash": 2, "nequival": 2, "tcurrent": 2, "tnon": 2, "t27": 2, "nlevel": 2, "nmonei": 2, "t778": 2, "nmutual": 2, "n515": 2, "t105": 2, "t617": 2, "nsubtot": 2, "293": 2, "395": 2, "nu": 2, "treasuri": 2, "516": 2, "t212": 2, "087": 2, "380": 2, "agenc": 2, "159": 2, "t703": 2, "t17": 2, "568": 2, "158": 2, "810": 2, "ncertif": 2, "deposit": 2, "t873": 2, "t387": 2, "t478": 2, "066": 2, "ncorpor": 2, "t65": 2, "622": 2, "t270": 2, "953": 2, "939": 2, "027": 2, "t47": 2, "886": 2, "nmunicip": 2, "t412": 2, "t405": 2, "t190": 2, "nmortgag": 2, "595": 2, "t175": 2, "403": 2, "t23": 2, "367": 2, "278": 2, "t132": 2, "t583": 2, "635": 2, "t128": 2, "056": 2, "966": 2, "t34": 2, "t160": 2, "t688": 2, "650": 2, "36": 2, "359": 2, "t481": 2, "n442": 2, "t428": 2, "t923": 2, "t909": 2, "406": 2, "114": 2, "468": 2, "136": 2, "t271": 2, "533": 2, "048": 2, "491": 2, "332": 2, "t320": 2, "t608": 2, "t76": 2, "840": 2, "956": 2, "890": 2, "t20": 2, "627": 2, "243": 2, "t628": 2, "t602": 2, "t192": 2, "t410": 2, "735": 2, "636": 2, "t344": 2, "t144": 2, "470": 2, "657": 2, "831": 2, "125": 2, "162": 2, "t173": 2, "752": 2, "quot": 2, "corrobor": 2, "mortgag": 2, "classifi": 2, "37": 2, "cross": 2, "swap": 2, "remeasur": 2, "notion": 2, "069": 2, "730": 2, "575": 2, "493": 2, "t104": 2, "777": 2, "nhedg": 2, "433": 2, "505": 2, "247": 2, "ntrade": 2, "41": 2, "44": 2, "depreci": 2, "nland": 2, "690": 2, "nmachineri": 2, "t80": 2, "205": 2, "314": 2, "nleasehold": 2, "839": 2, "128": 2, "599": 2, "73": 2, "70": 2, "884": 2, "852": 2, "t55": 2, "335": 2, "906": 2, "601": 2, "703": 2, "010": 2, "457": 2, "634": 2, "391": 2, "neuropean": 2, "opinion": 2, "1991": 2, "2007": 2, "irish": 2, "branch": 2, "2003": 2, "2014": 2, "2015": 2, "request": [2, 3, 4], "minist": 2, "juli": 2, "annul": 2, "ecj": 2, "hear": 2, "asid": 2, "confirm": 2, "via": [2, 4], "unrecogn": 2, "nfeder": 2, "571": 2, "080": 2, "644": 2, "265": 2, "801": 2, "726": 2, "570": 2, "298": 2, "49": 2, "t84": 2, "428": 2, "603": 2, "483": 2, "t347": 2, "t669": 2, "076": 2, "830": 2, "419": 2, "072": 2, "pretax": 2, "72": 2, "71": 2, "ncomput": 2, "885": 2, "012": 2, "124": 2, "518": 2, "nimpact": 2, "n10": 2, "246": 2, "311": 2, "366": 2, "397": 2, "153": 2, "nexcess": 2, "893": 2, "871": 2, "192": 2, "739": 2, "ntax": 2, "carryforward": 2, "302": 2, "naccru": 2, "413": 2, "421": 2, "nunreal": 2, "173": 2, "168": 2, "873": 2, "743": 2, "nless": 2, "374": 2, "007": 2, "369": 2, "551": 2, "998": 2, "nright": 2, "179": 2, "nminimum": 2, "674": 2, "940": 2, "t511": 2, "t455": 2, "t490": 2, "805": 2, "202": 2, "indefinit": 2, "temporari": 2, "727": 2, "044": 2, "284": 2, "ndecreas": 2, "386": 2, "463": 2, "982": 2, "542": 2, "936": 2, "070": 2, "expir": 2, "statut": 2, "229": 2, "494": 2, "closur": 2, "intercompani": 2, "exceed": 2, "multiyear": 2, "exercis": 2, "noncash": 2, "rou": 2, "tfinanci": 2, "t2024": 2, "tother": 2, "661": 2, "tproperti": 2, "015": 2, "303": 2, "676": 2, "t165": 2, "t752": 2, "t859": 2, "430": 2, "842": 2, "tfinanc": 2, "n2025": 2, "820": 2, "t171": 2, "991": 2, "n2026": 2, "914": 2, "n2027": 2, "t59": 2, "733": 2, "n2028": 2, "360": 2, "t38": 2, "398": 2, "n2029": 2, "187": 2, "nthereaft": 2, "t837": 2, "undiscount": 2, "790": 2, "imput": 2, "376": 2, "534": 2, "t896": 2, "weight": 2, "borrow": 2, "implicit": 2, "readili": 2, "42": 2, "proce": 2, "nine": 2, "00": 2, "nmatur": 2, "333": 2, "264": 2, "948": 2, "645": 2, "309": 2, "arrear": 2, "namount": 2, "n2013": 2, "nfix": 2, "2062": 2, "t97": 2, "341": 2, "03": 2, "65": 2, "t106": 2, "572": 2, "n97": 2, "nunamort": 2, "premium": 2, "321": 2, "358": 2, "113": 2, "662": 2, "convert": [2, 4], "930": 2, "342": 2, "800": 2, "180": 2, "43": 2, "88": 2, "ndure": 2, "425": 2, "426": 2, "372": 2, "589": 2, "055": 2, "appreci": 2, "four": 2, "holder": 2, "n2014": 2, "bonu": 2, "nrestrict": 2, "nnumber": 2, "nrsu": 2, "ngrant": 2, "naggreg": 2, "nfair": 2, "nbalanc": 2, "t240": 2, "427": 2, "t75": 2, "t150": 2, "861": 2, "501": 2, "768": 2, "87": 2, "101": 2, "878": 2, "144": 2, "t127": 2, "t135": 2, "91": 2, "456": 2, "78": 2, "59": 2, "t140": 2, "80": 2, "326": 2, "t158": 2, "204": 2, "350": 2, "002": [2, 3], "nuncondit": 2, "uncondit": 2, "206": 2, "440": 2, "156": 2, "t633": 2, "t670": 2, "226": 2, "45": 2, "nconting": 2, "least": 2, "accrual": 2, "nconcentr": 2, "attribut": [2, 4], "46": 2, "t67": 2, "098": 2, "082": 2, "062": 2, "569": 2, "895": 2, "458": 2, "207": 2, "nonrecur": 2, "t142": 2, "196": 2, "t138": 2, "t147": 2, "859": 2, "nchina": 2, "n66": 2, "t181": 2, "887": 2, "t172": 2, "269": 2, "nlong": 2, "664": 2, "n4": 2, "797": 2, "778": 2, "219": 2, "47": 2, "nopinion": 2, "nwe": 2, "fairli": 2, "pcaob": 2, "criteria": 2, "sponsor": 2, "treadwai": 2, "2013": 2, "unqualifi": 2, "thereon": 2, "nthese": 2, "misstat": 2, "fraud": 2, "ndescript": 2, "naudit": 2, "nhow": 2, "nmatter": 2, "qualifi": 2, "letter": 2, "advisor": 2, "ernst": 2, "young": 2, "llp": 2, "auditor": 2, "2009": 2, "nsan": 2, "jose": 2, "nnovemb": 2, "coso": 2, "nour": 2, "ndefinit": 2, "pertain": 2, "mainten": 2, "accur": [2, 4], "disposit": 2, "receipt": 2, "degre": 2, "nevalu": 2, "nbase": 2, "supervis": 2, "13a": 2, "15d": 2, "summar": [2, 3], "ninher": 2, "met": 2, "appear": [2, 4], "paragraph": 2, "51": [2, 4], "ninsid": 2, "deirdr": 2, "brien": 2, "vice": 2, "presid": 2, "affirm": 2, "april": 2, "withhold": 2, "remitt": 2, "jeff": 2, "william": 2, "mr": 2, "insid": 2, "copi": [2, 3], "exhibit": 2, "solicit": 2, "document": [2, 3, 4], "id": 2, "00042": 2, "nincorpor": 2, "texhibit": 2, "descript": [2, 4], "tform": 2, "tfile": 2, "nrestat": 2, "n8": 2, "namend": 2, "bylaw": 2, "nindentur": 2, "york": [2, 4], "mellon": 2, "truste": 2, "noffic": 2, "certif": 2, "2018": 2, "85": 2, "2043": 2, "05": 2, "2044": 2, "februari": 2, "55": 2, "2045": 2, "900": 2, "700": 2, "60": 2, "250": 2, "2036": 2, "2046": 2, "450": 2, "2047": 2, "2049": 2, "2030": 2, "2050": 2, "2060": 2, "2028": 2, "2041": 2, "2051": 2, "2061": 2, "2032": 2, "2052": 2, "54": 2, "2033": 2, "2053": 2, "n9": 2, "ceo": 2, "n12": 2, "nsubsidiari": 2, "n23": 2, "nconsent": 2, "n24": 2, "npower": 2, "signatur": 2, "nrule": 2, "nsection": 2, "1350": 2, "n101": 2, "ninlin": 2, "xbrl": 2, "n104": 2, "inlin": 2, "compensatori": 2, "herewith": 2, "furnish": 2, "herebi": 2, "undertak": 2, "56": 2, "nsignatur": 2, "npursuant": 2, "duli": 2, "sign": 2, "undersign": 2, "thereunto": 2, "ndate": 2, "nby": 2, "luca": [2, 4], "maestri": 2, "nluca": 2, "nsenior": 2, "nchief": 2, "nknow": 2, "THESE": 2, "whose": 2, "constitut": 2, "appoint": 2, "timothi": 2, "cook": 2, "jointli": 2, "hi": [2, 4], "her": 2, "substitut": 2, "him": 2, "thereto": 2, "therewith": 2, "ratifi": 2, "said": 2, "done": [2, 4], "virtu": 2, "hereof": 2, "nname": 2, "ttitl": 2, "tdate": 2, "tchief": 2, "tnovemb": 2, "ntimothi": 2, "tsenior": 2, "chri": 2, "kondo": 2, "nchri": 2, "wanda": 2, "austin": 2, "nwanda": 2, "alex": 2, "gorski": 2, "tdirector": 2, "nalex": 2, "andrea": 2, "jung": 2, "nandrea": 2, "arthur": 2, "levinson": 2, "narthur": 2, "monica": 2, "lozano": 2, "nmonica": 2, "ronald": 2, "sugar": 2, "nronald": 2, "susan": 2, "l": 2, "wagner": 2, "nsusan": 2, "57": 2, "gpt": [2, 3, 4], "turbo": [2, 3, 4], "invdestacksmeticsisdict": 2, "setispect": 2, "20cyan": 2, "evaluationseld": 2, "anvis": 2, "droitent": 2, "discernminerv": 2, "versbobprefvers": 2, "vo\u8be5": 2, "option\u548c": 2, "meio": 2, "\u0432\u0440\u0435\u043ccisco": 2, "dellaischenpoihscap": 2, "geme": 2, "gettim": 2, "radic": 2, "grappl": 2, "probabilist": 2, "seem": [2, 4], "safer": 2, "don": [2, 3, 4], "highlight": [2, 3, 4], "paradigm": 2, "anoth": 2, "fascin": 2, "spontan": 2, "answer": [2, 3, 4], "aren": 2, "explicitli": 2, "pre": 2, "fig": [2, 3, 4], "linear": 2, "absent": 2, "simpli": [2, 3, 4], "coax": 2, "onc": [2, 3], "reach": [2, 3, 4], "journei": 2, "suddenli": 2, "manifest": 2, "call": [2, 3, 4], "phase": 2, "stark": 2, "deliber": 2, "wei": 2, "convent": 2, "stabl": 2, "suit": 2, "contend": 2, "7b": 2, "70b": 2, "rethink": 2, "math": 2, "tutor": 2, "children": 2, "verifi": [2, 4], "just": [2, 3, 4], "predefin": [2, 4], "adapt": [2, 3], "explan": [2, 4], "child": 2, "ag": 2, "bound": 2, "weren": 2, "accuraci": [2, 4], "kind": 2, "dimens": 2, "explicit": [2, 4], "usual": 2, "precis": [2, 4], "resist": 2, "straightforward": [2, 3, 4], "quantif": 2, "contamin": 2, "carefulli": [2, 4], "craft": [2, 4], "massiv": 2, "alreadi": 2, "seen": 2, "memor": 2, "truli": 2, "unseen": 2, "rigor": 2, "evolut": 2, "longitudin": 2, "autom": [2, 4], "annot": 2, "mostli": [2, 4], "versu": 2, "latter": 2, "foundat": [2, 3], "tailor": 2, "solv": [2, 4], "great": [2, 4], "cognit": 2, "meta": [2, 3], "why": [2, 4], "misinform": 2, "factual": 2, "databas": [2, 4], "citat": 2, "tempor": 2, "scientif": 2, "fals": [2, 4], "manipul": 2, "medic": 2, "disclaim": 2, "referr": 2, "boundari": 2, "situat": [2, 3], "incorrect": 2, "expertis": 2, "bia": [2, 4], "gender": 2, "racial": 2, "demograph": 2, "stereotyp": 2, "reinforc": 2, "societ": 2, "pii": 2, "anonym": 2, "leakag": 2, "carryov": 2, "protocol": 2, "multi": [2, 4], "mathemat": 2, "fallaci": 2, "causal": 2, "edg": 2, "think": 2, "idiom": 2, "sarcasm": 2, "terminologi": 2, "lingual": 2, "misunderstand": 2, "syntax": 2, "scan": 2, "compat": [2, 4], "stabil": 2, "effici": [2, 3, 4], "scalabl": [2, 3], "overconfid": 2, "clariti": [2, 3, 4], "audienc": 2, "densiti": 2, "satisfact": [2, 4], "misus": 2, "moral": 2, "transpar": [2, 4], "co2": 2, "energi": 2, "consumpt": 2, "server": [2, 4], "batch": 2, "infer": 2, "imag": 2, "audio": 2, "etc": [2, 4], "truth": [2, 4], "layer": [2, 3, 4], "palm": 2, "shown": 2, "quantifi": 2, "rank": 2, "easi": [2, 3], "synthet": [2, 4], "post": [2, 4], "timeout": 2, "variat": 2, "maxim": 2, "inter": 2, "rater": 2, "priorit": 2, "ti": 2, "tier": 2, "holist": 2, "built": [2, 4], "mind": 2, "x": 2, "fast": [2, 4], "experiment": [2, 4], "iter": [2, 3, 4], "vi": 2, "later": [2, 4], "categor": [2, 4], "intrins": 2, "extrins": 2, "sequenc": [2, 4], "perplex": 2, "downstream": [2, 4], "valuabl": [2, 4], "distinguish": 2, "classif": [2, 4], "true": [2, 3, 4], "synthesi": 2, "discret": 2, "f1": 2, "match": [2, 4], "prefix": 2, "roug": 2, "bleu": 2, "charact": [2, 3, 4], "gram": 2, "bilingu": 2, "understudi": 2, "overlap": [2, 3], "favor": [2, 4], "breviti": 2, "insensit": 2, "semant": [2, 3], "orient": 2, "gist": 2, "sentenc": [2, 3, 4], "ignor": 2, "meteor": 2, "synonym": 2, "stem": [2, 4], "paraphras": 2, "alongsid": 2, "computation": [2, 3], "cider": 2, "consensu": 2, "tf": 2, "idf": 2, "caption": 2, "reliant": 2, "corpu": 2, "statist": 2, "ter": 2, "edit": 2, "hypothesi": 2, "penal": 2, "bertscor": 2, "embed": [2, 3], "bert": 2, "spice": 2, "proposit": 2, "scene": 2, "emphasi": 2, "pure": 2, "analyst": [2, 3], "dictionari": [2, 4], "rouge_1": 2, "rouge_2": 2, "ideal": [2, 4], "expert": [2, 3, 4], "cheaper": 2, "4o": [2, 3, 4], "evaluate_summari": 2, "unigram": 2, "bigram": 2, "huggingfac": 2, "librari": [2, 3, 4], "absl": 2, "py": 2, "rouge_scor": 2, "generated_summari": 2, "reference_summari": 2, "arg": [2, 3, 4], "dict": [2, 3, 4], "google_bleu": 2, "bleu_scor": 2, "rouge1": 2, "rouge2": 2, "arbitrari": 2, "chosen": 2, "sentence1": 2, "cat": 2, "sat": 2, "mat": 2, "sentence2": 2, "ate": 2, "3333333333333333": 2, "7272727272727272": 2, "4444444444444445": 2, "generate_summari": 2, "summir": 2, "correspond": [2, 4], "liner": 2, "excerpt": 2, "evaluate_summary_model": 2, "model_benchmark": 2, "models_test": 2, "benchmark_summari": 2, "model_summari": 2, "evaluation_result": 2, "reveal": 2, "analyz": [2, 3, 4], "statu": 2, "concis": 2, "element": [2, 4], "Its": 2, "verbos": 2, "peripher": 2, "quit": [2, 4], "overli": [2, 4], "simplifi": [2, 4], "miss": 2, "convei": [2, 3], "breadth": 2, "Of": 2, "vibe": 2, "visualize_prompt_comparison": 2, "visual": 2, "matplotlib": 2, "radar": 2, "plot": 2, "radar_plot": 2, "tmp": 2, "ipykernel_1652501": 2, "940173201": 2, "userwarn": 2, "figurecanvasagg": 2, "closest": 2, "largest": 2, "deviat": [2, 4], "suggest": [2, 4], "mention": [2, 4], "nuanc": [2, 3, 4], "granular": [2, 3], "fall": 2, "judg": 2, "themselv": 2, "main": [2, 3, 4], "instruct": [2, 3, 4], "tune": [2, 4], "assign": [2, 4], "likert": 2, "style": 2, "pairwis": 2, "ensembl": 2, "repeatedli": 2, "domain": 2, "clear": [2, 4], "fluenci": 2, "refin": 2, "excel": [2, 4], "narr": 2, "mirror": 2, "similarli": 2, "notabl": [2, 4], "properli": [2, 4], "henc": 2, "worth": 2, "integ": 2, "rubric": 2, "hollist": 2, "judgeevalu": 2, "grammar": [2, 4], "evaluate_with_llm": 2, "candid": 2, "pars": [2, 4], "criterion": 2, "basemodel": [2, 4], "judge_model": 2, "candidate_summari": 2, "written": 2, "grammat": 2, "y": [2, 4], "z": 2, "w": [2, 3], "beta": [2, 4], "response_format": [2, 4], "Then": 2, "benchmark_model": 2, "test_model": 2, "input_text": [2, 3], "tupl": 2, "trillion": [2, 4], "evals_list": 2, "1775618912": 2, "variant": 2, "slightli": 2, "drift": 2, "lowest": 2, "drop": 2, "gradient": 2, "visibl": 2, "degrad": [2, 4], "firstli": 2, "overhead": 2, "neglect": 2, "prefer": [2, 4], "egocentr": 2, "tight": 2, "field": [2, 4], "aproach": 2, "workflow": [2, 4], "assessor": 2, "aplic": 2, "aim": [2, 3, 4], "clearli": [2, 4], "earlier": 2, "depict": [2, 4], "correl": 2, "multilingu": 2, "golden": 2, "languang": 2, "arena": 2, "blind": 2, "randomli": 2, "pair": 2, "loop": 2, "customiz": 2, "irrelev": 2, "unhelp": 2, "though": [2, 4], "occasion": 2, "rare": 2, "inaccuraci": 2, "perfectli": 2, "cater": 2, "critiqu": 2, "elo": 2, "democrat": [2, 4], "thought": [2, 4], "exam": 2, "probe": 2, "certifi": 2, "histori": 2, "move": [2, 3], "began": 2, "glue": 2, "wang": 2, "entail": 2, "baselin": 2, "superglu": 2, "deeper": [2, 3], "successor": 2, "grew": 2, "big": 2, "bench": 2, "srivastava": 2, "arithmet": 2, "truthfulqa": 2, "lin": [2, 4], "decept": 2, "multitask": 2, "hendryck": 2, "multidisciplinari": 2, "stanford": 2, "helm": 2, "liang": 2, "multidimension": 2, "surround": [2, 4], "emphas": [2, 4], "humanev": 2, "chen": [2, 4], "lmsy": 2, "brought": 2, "dialogu": 2, "len": [2, 3], "replic": [2, 4], "chatbot": 2, "chiang": 2, "gather": 2, "alpacaev": 2, "duboi": 2, "mt": 2, "zheng": 2, "Their": [2, 4], "render": 2, "crowdsourc": 2, "livebench": 2, "white": 2, "resili": 2, "meaningfulli": 2, "monthli": 2, "zebralog": 2, "grid": 2, "puzzl": 2, "brailsford": 2, "1999": 2, "lsat": 2, "hous": 2, "clue": 2, "strateg": [2, 4], "deduct": 2, "arriv": 2, "programmat": [2, 4], "2x2": 2, "6x6": 2, "reductio": 2, "ad": [2, 4], "absurdum": 2, "sonnet": [2, 3], "hard": 2, "10b": 2, "counterfactu": 2, "composit": 2, "came": 2, "arc": 2, "prize": 2, "chollet": 2, "mike": 2, "knoop": 2, "founder": 2, "zapier": 2, "fran\u00e7oi": 2, "creator": 2, "agi": 2, "kera": 2, "meaning": [2, 3, 4], "genuin": 2, "old": 2, "possess": 2, "count": [2, 3], "elementari": 2, "novelti": 2, "someth": 2, "wouldn": 2, "interpol": 2, "memori": [2, 3], "synthes": 2, "fly": 2, "brute": 2, "minim": [2, 4], "pixel": 2, "perfect": 2, "color": 2, "unbeaten": 2, "win": 2, "deep": [2, 4], "poorli": 2, "recombin": 2, "spur": 2, "art": 2, "takeawai": 2, "algorithm": 2, "fourrier": 2, "lightweight": [2, 4], "bespok": 2, "sdk": 2, "cli": 2, "extract": [2, 3, 4], "autoregress": 2, "sub": 2, "liter": 2, "disturb": 2, "zero": [2, 4], "varianc": 2, "yt": 2, "ut": 2, "suppos": [2, 4], "exactli": [2, 4], "ol": 2, "heteroscedast": 2, "regress": 2, "wish": 2, "lag": 2, "bivari": 2, "evaluation_track": 2, "evaluationtrack": 2, "model_config": 2, "basemodelconfig": 2, "parallelismmanag": 2, "pipelineparamet": 2, "envconfig": 2, "is_accelerate_avail": 2, "datetim": 2, "timedelta": 2, "initprocessgroupkwarg": 2, "create_evaluation_pipelin": 2, "output_dir": 2, "cache_dir": 2, "pretrain": 2, "dtype": 2, "float16": 2, "max_sampl": 2, "kwargs_handl": 2, "3000": 2, "els": [2, 3], "save_detail": 2, "push_to_hub": 2, "pipeline_param": 2, "launcher_typ": 2, "env_config": 2, "override_batch_s": 2, "use_chat_templ": 2, "trust_remote_cod": 2, "pipeline_paramet": 2, "schemat": [2, 3], "vllm": [2, 4], "tgi": 2, "instanti": 2, "storag": 2, "push": 2, "hub": 2, "parallel": 2, "num_few_shot": 2, "automat": 2, "string": [2, 4], "vertic": 2, "bar": 2, "binari": 2, "flag": 2, "bigbench": 2, "winogrand": 2, "hellaswag": 2, "nlp": 2, "save_and_push_result": 2, "show_result": 2, "model_arg": 2, "remot": 2, "send": [2, 4], "serverless": 2, "inference_server_address": 2, "inference_server_auth": 2, "model_id": 2, "null": 2, "bash": 2, "command": 2, "model_config_path": 2, "path": [2, 3], "endpoint_model": 2, "yaml": [2, 4], "llama3": [2, 3], "qwen2": [2, 4], "smollm2": 2, "3b": 2, "alibaba": [2, 4], "5b": [2, 4], "hui": 2, "yang": 2, "compact": 2, "360m": 2, "allal": 2, "cluster": 2, "noteworthi": 2, "superior": 2, "grain": [2, 4], "salt": [2, 4], "give": 2, "exponenti": 2, "hug": 2, "modular": 2, "visit": 2, "offici": 2, "revisit": 2, "rememb": 2, "api_kei": [2, 3], "trace": 2, "langchain_tracing_v2": 2, "langchain_api_kei": 2, "hf_evalu": 2, "langsmith_evalu": 2, "ls_client": 2, "dataset_nam": 2, "create_dataset": 2, "create_exampl": 2, "dataset_id": 2, "calculate_scor": 2, "reference_output": 2, "oai_client": 2, "xp_model_nam": 2, "lastli": 2, "run_evalu": 2, "upload": 2, "And": 2, "upload_result": 2, "experiment_prefix": 2, "num_repetit": 2, "view": 2, "386a3620": 2, "smith": 2, "9e1cc3cb": 2, "9d6a": 2, "4356": 2, "ab34": 2, "138e0abe8be4": 2, "8741976e": 2, "5268": 2, "4b75": 2, "949f": 2, "99477dde5d64": 2, "selectedsess": 2, "b831dc1e": 2, "90bc": 2, "4ed8": 2, "8080": 2, "fb42444724d6": 2, "4it": 2, "latest": [2, 3, 4], "modul": [2, 4], "tobia": 2, "evaluate_modul": 2, "6fc70b7be0088120a372dfdd5d320b39b8bb3630cb8029b193941d9376e86bb0": 2, "tue": 2, "nov": 2, "couldn": 2, "5it": 2, "5053784e": 2, "64445871": 2, "a53c": 2, "44b1": 2, "a422": 2, "4f49b2f9656f": 2, "69": 2, "4b29f3c9": 2, "9ef7e39a": 2, "2add": 2, "410c": 2, "89f8": 2, "9f1a8b198cf1": 2, "61": 2, "df": 2, "to_panda": 2, "insert": 2, "combined_df": 2, "concat": 2, "ignore_index": 2, "execution_tim": 2, "example_id": 2, "333333": 2, "224388": 2, "feb10f92": 2, "3167": 2, "41f3": 2, "bb1c": 2, "d271153a31a8": 2, "5b196b22": 2, "9f4c": 2, "489c": 2, "b020": 2, "7823208b42d6": 2, "348101": 2, "722464": 2, "c310f159": 2, "064a": 2, "4035": 2, "97c3": 2, "a25bbf43abc2": 2, "386076": 2, "704104": 2, "f7f24899": 2, "dd50": 2, "409e": 2, "93cc": 2, "6fb1622b60bf": 2, "443038": 2, "725059": 2, "242856d6": 2, "efb5": 2, "4101": 2, "b1cf": 2, "5805532838ac": 2, "373418": 2, "795302": 2, "ce975169": 2, "a0ab": 2, "40ce": 2, "8e32": 2, "efa28d06079d": 2, "stat": 2, "groupbi": 2, "agg": 2, "std": 2, "round": 2, "sort": 2, "sort_valu": 2, "figur": [2, 4], "subplot": 2, "side": 2, "pyplot": 2, "plt": 2, "numpi": 2, "np": 2, "ax1": 2, "ax2": 2, "figsiz": 2, "2ecc71": 2, "3498db": 2, "e74c3c": 2, "bleu_mean": 2, "bleu_std": 2, "enumer": [2, 3], "errorbar": 2, "yerr": 2, "fmt": 2, "markers": 2, "capsiz": 2, "label": [2, 4], "alpha": [2, 4], "set_ylabel": 2, "set_titl": 2, "set_xtick": 2, "set_xticklabel": 2, "rotat": 2, "set_ylim": 2, "bottom": 2, "axi": 2, "legend": 2, "exec_mean": 2, "exec_std": 2, "tight_layout": 2, "ndetail": 2, "4038": 2, "0453": 2, "7815": 2, "0433": 2, "3768": 2, "0424": 2, "8343": 2, "2208": 2, "3519": 2, "0775": 2, "9122": 2, "1482": 2, "377": 2, "042": 2, "83": 2, "078": 2, "slower": 2, "fastest": 2, "04": [2, 3], "latenc": [2, 3], "speed": 2, "interestingli": 2, "longer": 2, "decoupl": 2, "friendli": [2, 3], "reload": 2, "facilit": 2, "pleas": 2, "promptfooconfig": 2, "model_comparison": 2, "config": 2, "safe_load": 2, "pretti": 2, "dump": 2, "default_flow_styl": 2, "sort_kei": 2, "prompt1": 2, "defaulttest": 2, "1000": 2, "ye": [2, 4], "csv": 2, "1000m": 2, "sure": [2, 3, 4], "millisecond": 2, "eval_data": 2, "latency_m": 2, "totallatencym": 2, "token_usag": 2, "tokenusag": 2, "assert_pass": 2, "assertpasscount": 2, "assert_fail": 2, "assertfailcount": 2, "prompt_token": 2, "num_request": 2, "numrequest": 2, "ipython": 2, "markdown": [2, 3], "2463": 2, "000035": 2, "3773": 2, "004620": 2, "1669": 2, "000091": 2, "1669m": 2, "highest": 2, "3773m": 2, "00462": 2, "promptfool": 2, "manual": 2, "redefin": 2, "prompt_comparison": 2, "prompt2": 2, "prompt3": 2, "Not": 2, "prompt_fil": 2, "prompt_cont": 2, "strip": 2, "join": [2, 3], "BE": 2, "again": 2, "prompt_id": 2, "promptid": 2, "gradingresult": 2, "split": [2, 3], "df_raw": 2, "column": 2, "pivot": 2, "reset_index": 2, "eas": 2, "seamless": 2, "hf": 2, "quick": 2, "plain": 2, "vanilla": 2, "ui": [2, 4], "alb": 2, "loubna": 2, "ben": 2, "anton": 2, "lozhkov": 2, "eli": 2, "bakouch": 2, "gabriel": 2, "mart\u00edn": 2, "bl\u00e1zquez": 2, "lewi": 2, "tunstal": 2, "agust\u00edn": 2, "piquer": 2, "andr": 2, "marafioti": 2, "cyril": 2, "zakka": 2, "leandro": 2, "von": 2, "werra": 2, "thoma": 2, "wolf": 2, "are24": 2, "judgearena": 2, "bps99": 2, "salli": 2, "pott": 2, "barbara": 2, "557": 2, "sciencedirect": 2, "s0377221798003646": 2, "doi": [2, 4], "org": [2, 4], "1016": 2, "s0377": 2, "2217": 2, "00364": 2, "ctj": 2, "jerri": 2, "tworek": 2, "heewoo": 2, "jun": 2, "qime": 2, "yuan": 2, "henriqu": 2, "pond": 2, "de": 2, "oliveira": 2, "pinto": 2, "jare": 2, "kaplan": 2, "harri": 2, "edward": 2, "yuri": 2, "burda": 2, "nichola": 2, "joseph": 2, "greg": 2, "brockman": 2, "rai": 2, "raul": 2, "puri": 2, "gretchen": 2, "krueger": 2, "michael": [2, 4], "petrov": 2, "heidi": 2, "khlaaf": 2, "girish": 2, "sastri": 2, "pamela": 2, "mishkin": 2, "brook": 2, "chan": 2, "scott": 2, "grai": 2, "nick": 2, "ryder": 2, "mikhail": 2, "pavlov": 2, "alethea": 2, "lukasz": 2, "kaiser": 2, "mohammad": 2, "bavarian": 2, "clemen": 2, "winter": 2, "philipp": 2, "tillet": 2, "felip": 2, "petroski": 2, "dave": 2, "cum": 2, "matthia": 2, "plappert": 2, "fotio": 2, "chantzi": 2, "elizabeth": 2, "barn": 2, "ariel": 2, "herbert": 2, "voss": 2, "hebgen": 2, "guss": 2, "nichol": 2, "paino": 2, "nikola": 2, "tezak": 2, "jie": 2, "tang": 2, "igor": 2, "babuschkin": 2, "suchir": 2, "balaji": 2, "shantanu": 2, "jain": 2, "saunder": 2, "christoph": 2, "hess": 2, "andrew": 2, "carr": 2, "jan": 2, "leik": 2, "josh": 2, "achiam": 2, "vedant": 2, "misra": 2, "evan": 2, "morikawa": 2, "alec": 2, "radford": 2, "matthew": 2, "knight": 2, "mile": 2, "brundag": 2, "mira": 2, "murati": 2, "kati": 2, "mayer": 2, "peter": 2, "welind": 2, "bob": [2, 4], "mcgrew": 2, "dario": 2, "amodei": 2, "sam": 2, "mccandlish": 2, "ilya": 2, "sutskev": 2, "wojciech": 2, "zaremba": 2, "arxiv": [2, 4], "ab": [2, 4], "2107": 2, "03374": 2, "cz": 2, "lianmin": 2, "ying": 2, "sheng": 2, "anastasio": 2, "angelopoulo": 2, "tianl": 2, "dacheng": 2, "hao": 2, "zhang": 2, "banghua": 2, "zhu": 2, "jordan": 2, "gonzalez": 2, "ion": 2, "stoica": 2, "2403": 2, "04132": 2, "cho24a": 2, "francoi": 2, "arcpriz": 2, "cho24b": 2, "dglh24": 2, "yann": 2, "bal\u00e1z": 2, "galambosi": 2, "perci": 2, "tatsunori": 2, "hashimoto": 2, "debia": 2, "2404": 2, "04475": 2, "fac24a": 2, "wiki": [2, 4], "fac24b": 2, "fac24c": 2, "doc": [2, 3, 4], "model_doc": 2, "gpt2": 2, "fac24d": 2, "cookbook": 2, "en": [2, 4], "llm_judg": 2, "fac24": 2, "fac24f": 2, "blog": [2, 4], "fhwt23": 2, "cl\u00e9mentin": 2, "nathan": 2, "habib": 2, "hbb": 2, "dan": 2, "collin": 2, "burn": 2, "steven": 2, "basart": 2, "andi": 2, "zou": 2, "manta": 2, "mazeika": 2, "dawn": 2, "song": 2, "jacob": 2, "steinhardt": 2, "03300": 2, "hbd": 2, "ari": 2, "du": 2, "maxwel": 2, "forb": 2, "yejin": 2, "choi": 2, "curiou": 2, "neural": [2, 4], "degener": 2, "1904": 2, "09751": 2, "hyc": 2, "binyuan": 2, "jian": 2, "zeyu": 2, "cui": 2, "jiaxi": 2, "dayiheng": 2, "liu": [2, 4], "lei": 2, "tianyu": 2, "jiajun": 2, "bowen": 2, "yu": 2, "kai": 2, "dang": 2, "coder": 2, "preprint": [2, 4], "2409": 2, "12186": 2, "lx": 2, "zhen": 2, "xiaohan": 2, "xu": 2, "tao": 2, "shen": 2, "jia": 2, "gu": 2, "yuxuan": 2, "lai": 2, "chongyang": 2, "shuai": 2, "ma": 2, "nlg": 2, "2401": 2, "07103": 2, "lbl": 2, "rishi": 2, "bommasani": 2, "toni": 2, "lee": [2, 4], "dimitri": 2, "tsipra": 2, "dilara": 2, "soylu": 2, "michihiro": 2, "yasunaga": 2, "yian": 2, "deepak": 2, "narayanan": 2, "yuhuai": 2, "wu": [2, 4], "ananya": 2, "kumar": 2, "benjamin": 2, "newman": 2, "binhang": 2, "bobbi": 2, "yan": 2, "ce": 2, "christian": 2, "cosgrov": 2, "r\u00e9": 2, "diana": 2, "acosta": 2, "nava": 2, "drew": 2, "hudson": 2, "eric": 2, "zelikman": 2, "esin": 2, "durmu": 2, "faisal": 2, "ladhak": 2, "frieda": 2, "rong": 2, "hongyu": 2, "ren": 2, "huaxiu": 2, "yao": 2, "jue": 2, "keshav": 2, "santhanam": 2, "laurel": 2, "orr": 2, "lucia": 2, "mert": 2, "yuksekgonul": 2, "mirac": 2, "suzgun": 2, "kim": 2, "neel": 2, "guha": 2, "niladri": 2, "chatterji": 2, "omar": 2, "khattab": 2, "henderson": 2, "qian": 2, "huang": 2, "ryan": 2, "chi": [2, 4], "sang": 2, "xie": 2, "shibani": 2, "santurkar": 2, "surya": 2, "ganguli": 2, "icard": 2, "tianyi": 2, "vishrav": 2, "chaudhari": 2, "xuechen": 2, "yifan": 2, "yuhui": 2, "yuta": 2, "koreeda": 2, "2211": 2, "09110": 2, "lbc24": 2, "yuchen": 2, "ronan": 2, "le": 2, "bra": 2, "allenai": 2, "lhe22": 2, "stephani": 2, "hilton": 2, "owain": 2, "mimic": 2, "falsehood": 2, "2109": 2, "07958": 2, "pro24": 2, "dev": 2, "ras24": 2, "sebastian": 2, "scratch": 2, "isbn": 2, "1633437166": 2, "srr": 2, "aarohi": 2, "abhinav": 2, "rastogi": 2, "abhishek": 2, "rao": 2, "abu": 2, "awal": 2, "md": [2, 4], "shoeb": 2, "abubakar": 2, "abid": 2, "adam": 2, "fisch": 2, "brown": 2, "santoro": 2, "aditya": 2, "gupta": 2, "adri\u00e0": 2, "garriga": 2, "alonso": 2, "agnieszka": 2, "kluska": 2, "aitor": 2, "lewkowycz": 2, "akshat": 2, "agarw": 2, "warstadt": 2, "alexand": [2, 4], "kocurek": 2, "ali": 2, "safaya": 2, "tazarv": 2, "alic": [2, 4], "xiang": 2, "alicia": 2, "parrish": 2, "allen": 2, "nie": 2, "aman": 2, "hussain": 2, "amanda": 2, "askel": 2, "dsouza": 2, "ambros": 2, "slone": 2, "ameet": 2, "rahan": 2, "anantharaman": 2, "iyer": 2, "ander": 2, "andreassen": 2, "madotto": 2, "santilli": 2, "stuhlm\u00fcller": 2, "la": 2, "lampinen": 2, "angela": 2, "jiang": 2, "angelica": 2, "anh": 2, "vuong": 2, "animesh": 2, "anna": 2, "gottardi": 2, "antonio": 2, "norelli": 2, "anu": 2, "venkatesh": 2, "arash": 2, "gholamidavoodi": 2, "arfa": 2, "tabassum": 2, "arul": 2, "menez": 2, "arun": 2, "kirubarajan": 2, "asher": 2, "mullokandov": 2, "ashish": 2, "sabharw": 2, "herrick": 2, "avia": 2, "efrat": 2, "aykut": 2, "erdem": 2, "ayla": 2, "karaka\u015f": 2, "robert": 2, "bao": 2, "loe": 2, "barret": 2, "zoph": 2, "bart\u0142omiej": 2, "bojanowski": 2, "batuhan": 2, "\u00f6zyurt": 2, "behnam": 2, "hedayatnia": 2, "neyshabur": 2, "inden": 2, "benno": 2, "stein": 2, "berk": 2, "ekmekci": 2, "blake": 2, "howald": 2, "bryan": 2, "orinion": 2, "cameron": [2, 4], "diao": 2, "dour": 2, "catherin": 2, "stinson": 2, "cedrick": 2, "argueta": 2, "c\u00e9sar": 2, "ferri": 2, "ram\u00edrez": 2, "chandan": 2, "singh": 2, "charl": 2, "rathkopf": 2, "chenlin": 2, "meng": 2, "chitta": 2, "baral": 2, "chiyu": 2, "callison": 2, "burch": 2, "wait": 2, "voigt": 2, "cindi": 2, "ramirez": 2, "clara": 2, "rivera": 2, "clemencia": 2, "siro": 2, "colin": 2, "raffel": 2, "courtnei": 2, "ashcraft": 2, "cristina": 2, "garbacea": 2, "damien": 2, "sileo": 2, "garrett": 2, "kilman": 2, "roth": 2, "daniel": 2, "freeman": 2, "khashabi": 2, "levi": 2, "mosegu\u00ed": 2, "gonz\u00e1lez": 2, "perszyk": 2, "danni": 2, "hernandez": 2, "danqi": 2, "daphn": 2, "ippolito": 2, "dar": 2, "gilboa": 2, "david": 2, "dohan": 2, "drakard": 2, "jurgen": 2, "debajyoti": 2, "datta": 2, "deni": 2, "emelin": 2, "kleyko": 2, "deniz": 2, "yuret": 2, "derek": 2, "tam": [2, 4], "dieuwk": 2, "hupk": 2, "diganta": 2, "dilyar": 2, "buzan": 2, "coelho": 2, "mollo": 2, "diyi": 2, "dong": 2, "ho": 2, "dylan": 2, "schrader": 2, "ekaterina": 2, "shutova": 2, "ekin": 2, "dogu": 2, "cubuk": 2, "elad": 2, "segal": 2, "eleanor": 2, "hagerman": 2, "donowai": 2, "elli": 2, "pavlick": 2, "emanuel": 2, "rodola": 2, "emma": 2, "lam": 2, "chu": 2, "erkut": 2, "erni": 2, "ethan": 2, "dyer": 2, "jerzak": 2, "eunic": 2, "engefu": 2, "manyasi": 2, "evgenii": 2, "zheltonozhskii": 2, "fanyu": 2, "xia": 2, "fatemeh": 2, "siar": 2, "fernando": 2, "mart\u00ednez": 2, "plume": 2, "francesca": 2, "happ\u00e9": 2, "gaurav": 2, "mishra": 2, "genta": 2, "indra": 2, "winata": 2, "gerard": 2, "melo": 2, "germ\u00e1n": 2, "kruszewski": 2, "giambattista": 2, "parascandolo": 2, "giorgio": 2, "mariani": 2, "gloria": 2, "gonzalo": 2, "jaimovitch": 2, "l\u00f3pez": 2, "gregor": 2, "betz": 2, "gui": 2, "gur": 2, "hana": 2, "galijasev": 2, "hannah": 2, "rashkin": 2, "hannaneh": 2, "hajishirzi": 2, "harsh": 2, "mehta": 2, "hayden": 2, "bogar": 2, "henri": 2, "shevlin": 2, "hinrich": 2, "sch\u00fctze": 2, "hiromu": 2, "yakura": 2, "hongm": 2, "hugh": 2, "mee": 2, "wong": 2, "ian": 2, "ng": 2, "isaac": 2, "nobl": 2, "jaap": 2, "jumelet": 2, "jack": 2, "geissing": 2, "jackson": 2, "kernion": 2, "jaehoon": 2, "jaim": 2, "fern\u00e1ndez": 2, "fisac": 2, "jame": 2, "simon": 2, "koppel": 2, "koco\u0144": 2, "jana": 2, "thompson": 2, "janel": 2, "wingfield": 2, "jarema": 2, "radom": 2, "jascha": 2, "sohl": 2, "dickstein": 2, "jason": 2, "phang": 2, "yosinski": 2, "jekaterina": 2, "novikova": 2, "jell": 2, "bosscher": 2, "jennif": 2, "marsh": 2, "jeremi": 2, "jeroen": 2, "taal": 2, "jess": 2, "engel": 2, "jesujoba": 2, "alabi": 2, "jiacheng": 2, "jiam": 2, "jillian": 2, "joan": 2, "waweru": 2, "john": 2, "burden": 2, "miller": 2, "bali": 2, "jonathan": 2, "batcheld": 2, "berant": 2, "j\u00f6rg": 2, "frohberg": 2, "jo": 2, "rozen": 2, "orallo": 2, "boudeman": 2, "guerr": 2, "joshua": 2, "tenenbaum": 2, "joyc": 2, "chua": 2, "kamil": 2, "kanclerz": 2, "karen": 2, "livescu": 2, "karl": 2, "krauth": 2, "karthik": 2, "gopalakrishnan": 2, "katerina": 2, "ignatyeva": 2, "katja": 2, "markert": 2, "kaustubh": 2, "dhole": 2, "kevin": 2, "gimpel": 2, "omondi": 2, "kori": 2, "mathewson": 2, "kristen": 2, "chiafullo": 2, "ksenia": 2, "shkaruta": 2, "shridhar": 2, "kyle": 2, "mcdonel": 2, "richardson": 2, "laria": 2, "reynold": 2, "leo": 2, "gao": 2, "liam": 2, "dugan": 2, "lianhui": 2, "qin": 2, "lidia": 2, "contrera": 2, "ochando": 2, "loui": 2, "morenc": 2, "moschella": 2, "luci": 2, "ludwig": 2, "schmidt": 2, "luheng": 2, "lui": 2, "olivero": 2, "col\u00f3n": 2, "luke": 2, "metz": 2, "l\u00fctfi": 2, "kerem": 2, "\u015fenel": 2, "maarten": 2, "bosma": 2, "sap": 2, "maartj": 2, "hoev": 2, "maheen": 2, "farooqi": 2, "manaal": 2, "faruqui": 2, "marco": 2, "baturan": 2, "marelli": 2, "maru": 2, "maria": 2, "quintana": 2, "mari": 2, "tolkiehn": 2, "mario": 2, "giulianelli": 2, "martha": 2, "martin": 2, "potthast": 2, "leavitt": 2, "hagen": 2, "m\u00e1ty\u00e1": 2, "schubert": 2, "medina": 2, "orduna": 2, "baitemirova": 2, "melodi": 2, "arnaud": 2, "melvin": 2, "mcelrath": 2, "yee": 2, "cohen": 2, "ivanitskii": 2, "starritt": 2, "strube": 2, "micha\u0142": 2, "sw\u0119drowski": 2, "michel": 2, "bevilacqua": 2, "mihir": 2, "kale": 2, "cain": 2, "mime": 2, "mitch": 2, "walker": 2, "mo": 2, "tiwari": 2, "mohit": 2, "bansal": 2, "moin": 2, "aminnaseri": 2, "mor": 2, "geva": 2, "mozhdeh": 2, "gheini": 2, "mukund": 2, "varma": 2, "nanyun": 2, "peng": 2, "nayeon": 2, "neta": 2, "krakov": 2, "doiron": 2, "nicol": 2, "martinez": 2, "nikita": 2, "nangia": 2, "nikla": 2, "decker": 2, "muennighoff": 2, "nitish": 2, "shirish": 2, "keskar": 2, "niveditha": 2, "noah": 2, "constant": 2, "fiedel": 2, "nuan": 2, "wen": 2, "oliv": 2, "agha": 2, "elbaghdadi": 2, "omer": 2, "moreno": 2, "casar": 2, "parth": 2, "doshi": 2, "pascal": 2, "fung": 2, "paul": 2, "pu": 2, "vicol": 2, "pegah": 2, "alipoormolabashi": 2, "peiyuan": 2, "liao": 2, "eckerslei": 2, "phu": 2, "mon": 2, "htut": 2, "pinyu": 2, "hwang": 2, "piotr": 2, "mi\u0142kowski": 2, "piyush": 2, "patil": 2, "pouya": 2, "pezeshkpour": 2, "priti": 2, "oli": 2, "qiaozhu": 2, "mei": 2, "qing": 2, "lyu": 2, "qinlang": 2, "rabin": 2, "banjad": 2, "rachel": 2, "etta": 2, "rudolph": 2, "raefer": 2, "rahel": 2, "haback": 2, "ramon": 2, "risco": 2, "rapha\u00ebl": 2, "milli\u00e8r": 2, "rhythm": 2, "garg": 2, "rif": 2, "saurou": 2, "riku": 2, "arakawa": 2, "robb": 2, "raymaek": 2, "frank": 2, "rohan": 2, "sikand": 2, "roman": 2, "novak": 2, "sitelew": 2, "lebra": 2, "rosann": 2, "rowan": 2, "rui": [2, 4], "ruslan": 2, "salakhutdinov": 2, "stoval": 2, "teehan": 2, "rylan": 2, "sahib": 2, "saif": 2, "sajant": 2, "anand": 2, "dillav": 2, "shleifer": 2, "wiseman": 2, "samuel": 2, "gruetter": 2, "bowman": 2, "schoenholz": 2, "sanghyun": 2, "han": 2, "sanjeev": 2, "kwatra": 2, "sarah": 2, "sarik": 2, "ghazarian": 2, "sayan": 2, "ghosh": 2, "sean": 2, "casei": 2, "bischoff": 2, "gehrmann": 2, "schuster": 2, "sepideh": 2, "sadeghi": 2, "shadi": 2, "hamdan": 2, "sharon": 2, "zhou": 2, "shashank": 2, "sherri": 2, "shi": 2, "shikhar": 2, "shima": 2, "asaadi": 2, "shixiang": 2, "shane": 2, "shubh": 2, "pachchigar": 2, "shubham": 2, "toshniw": 2, "shyam": 2, "upadhyai": 2, "shyamolima": 2, "debnath": 2, "siamak": 2, "shakeri": 2, "thormey": 2, "melzi": 2, "siva": 2, "reddi": 2, "sneha": 2, "priscilla": 2, "makini": 2, "soo": 2, "hwan": 2, "spencer": 2, "toren": 2, "sriharsha": 2, "hatwar": 2, "stanisla": 2, "dehaen": 2, "stefan": 2, "divic": 2, "stefano": 2, "ermon": 2, "stella": 2, "biderman": 2, "stephen": 2, "prasad": 2, "piantadosi": 2, "stuart": 2, "shieber": 2, "summer": 2, "misherghi": 2, "svetlana": 2, "kiritchenko": 2, "swaroop": 2, "tal": 2, "linzen": 2, "tariq": 2, "tatsu": 2, "te": 2, "th\u00e9o": 2, "desbord": 2, "theodor": 2, "rothschild": 2, "phan": 2, "tiberiu": 2, "nkinyili": 2, "timo": 2, "schick": 2, "timofei": 2, "kornev": 2, "titu": 2, "tunduni": 2, "gerstenberg": 2, "trenton": 2, "trishala": 2, "neeraj": 2, "tushar": 2, "khot": 2, "tyler": 2, "shultz": 2, "uri": 2, "shaham": 2, "vera": 2, "demberg": 2, "victoria": 2, "nyamai": 2, "vika": 2, "raunak": 2, "vinai": 2, "ramasesh": 2, "udai": 2, "prabhu": 2, "vishakh": 2, "padmakumar": 2, "vivek": 2, "srikumar": 2, "fedu": 2, "wout": 2, "vossen": 2, "xiaoyu": 2, "tong": 2, "xinran": 2, "zhao": 2, "xinyi": 2, "xudong": 2, "yadollah": 2, "yaghoobzadeh": 2, "yair": 2, "lakretz": 2, "yangqiu": 2, "yasaman": 2, "bahri": 2, "yichi": 2, "yide": 2, "yifu": 2, "yonatan": 2, "belinkov": 2, "hou": 2, "yufang": 2, "yuntao": 2, "bai": 2, "zachari": 2, "seid": 2, "zhuoy": 2, "zijian": 2, "ziji": 2, "j": [2, 4], "zirui": 2, "ziyi": 2, "extrapol": 2, "2206": 2, "04615": 2, "wpn": 2, "yada": 2, "pruksachatkun": 2, "amanpreet": 2, "julian": 2, "felix": 2, "hill": 2, "stickier": 2, "wsm": 2, "1804": 2, "07461": 2, "wtb": 2, "yi": [2, 4], "tai": 2, "borgeaud": 2, "dani": 2, "yogatama": 2, "denni": 2, "donald": 2, "metzler": 2, "ed": 2, "h": 2, "oriol": 2, "vinyal": 2, "dean": 2, "07682": 2, "wdr": 2, "doolei": 2, "manlei": 2, "arka": 2, "pal": 2, "feuer": 2, "siddhartha": 2, "ravid": 2, "shwartz": 2, "ziv": 2, "khalid": 2, "saifullah": 2, "siddartha": 2, "naidu": 2, "chinmai": 2, "hegd": 2, "lecun": 2, "tom": 2, "goldstein": 2, "willi": 2, "neiswang": 2, "micah": 2, "goldblum": 2, "2406": 2, "19314": 2, "yyh": 2, "baosong": 2, "bo": 2, "chengpeng": 2, "chengyuan": 2, "fei": 2, "guant": 2, "haoran": 2, "huan": 2, "jialong": 2, "jialin": 2, "jianhong": 2, "tu": 2, "jianwei": 2, "jianxin": 2, "jin": 2, "jingren": 2, "jinz": 2, "jinzheng": 2, "junyang": 2, "keme": 2, "lu": 2, "keqin": 2, "kexin": 2, "mingfeng": 2, "xue": 2, "ni": 2, "pei": 2, "ru": 2, "men": 2, "ruiz": 2, "runji": 2, "shiji": 2, "sinan": 2, "tan": 2, "tianhang": 2, "tianhao": 2, "wenbin": 2, "ge": 2, "xiaodong": 2, "deng": 2, "xiaohuan": 2, "xingzhang": 2, "xinyu": 2, "xipin": 2, "xuancheng": 2, "fan": 2, "yichang": 2, "wan": 2, "yunfei": 2, "yuqiong": 2, "zhenru": 2, "zhihao": 2, "2407": 2, "10671": 2, "zc": 2, "siyuan": 2, "zhuang": 2, "zhanghao": 2, "yonghao": 2, "zi": 2, "zhuohan": 2, "xing": 2, "2306": 2, "05685": 2, "huggingface24": 2, "06": [2, 4], "metaai24": 2, "far": 3, "possibli": 3, "eliot": 3, "english": 3, "thumb": 3, "\u00be": 3, "max_output_token": 3, "4096": 3, "16384": 3, "contrari": 3, "surpass": 3, "truncat": 3, "max_input_token": 3, "input_cost_per_token": 3, "output_cost_per_token": 3, "11b": 3, "v1": 3, "128000": 3, "5e": 3, "20241022": 3, "8192": 3, "200000": 3, "3e": 3, "0613": 3, "6e": 3, "1e": 3, "gemini": 3, "flash": 3, "1048576": 3, "2097152": 3, "05e": 3, "incomplet": 3, "abruptli": 3, "shallow": 3, "thorough": 3, "dissatisfact": 3, "frustrat": 3, "creation": 3, "feasibl": 3, "10k": 3, "diagram": 3, "charactertextsplitt": 3, "tiktoken": 3, "sequenti": 3, "newlin": 3, "broadli": [3, 4], "want": [3, 4], "cheap": 3, "speciali": 3, "naiv": 3, "nltk": 3, "spaci": 3, "recurs": 3, "divid": 3, "hierarch": 3, "talk": 3, "theme": 3, "splitter": 3, "html": [3, 4], "get_chunk": 3, "chunk_siz": 3, "chunk_overlap": 3, "langchain_text_splitt": 3, "text_splitt": 3, "from_tiktoken_encod": 3, "split_text": 3, "persona": 3, "task": [3, 4], "langchain_cor": [3, 4], "prompttempl": 3, "get_base_prompt_templ": 3, "base_prompt": [3, 4], "from_templ": 3, "llmchain": 3, "togeth": 3, "parser": [3, 4], "output_pars": 3, "stroutputpars": 3, "langchain_commun": 3, "chat_model": 3, "chatlitellm": 3, "get_llm_chain": 3, "prompt_templ": [3, 4], "llm_chain": [3, 4], "api_key_label": 3, "upper": 3, "_api_kei": 3, "get_dynamic_prompt_templ": 3, "get_dynamic_prompt_param": 3, "prompt_param": 3, "part_idx": 3, "total_part": 3, "chat_context": 3, "param": 3, "dynamic_prompt_param": 3, "elif": 3, "merg": 3, "concaten": 3, "generate_report": 3, "input_cont": 3, "llm_model_nam": 3, "report_part": 3, "num_part": 3, "dinam": 3, "priovid": 3, "invok": [3, 4], "cummul": 3, "max_chunk_s": 3, "max_chunk_overlap": 3, "readabl": 3, "apple_report": 3, "luation": 3, "disciplin": 3, "smooth": 3, "subhead": 3, "despit": [3, 4], "depth": 3, "overlook": 3, "preserv": 3, "easier": [3, 4], "preprocess": [3, 4], "necessit": 3, "meticul": 3, "bottleneck": 3, "mustafa": 3, "suleyman": 3, "infinit": 3, "fewer": 3, "progress": 3, "condens": 3, "versatil": 3, "drive": [3, 4], "grace": 3, "fallback": 3, "empow": 3, "crucial": [3, 4], "langchain24": 3, "how_to": 3, "freedom": 4, "julia": 4, "easili": 4, "notebook": 4, "overrid": 4, "response_cont": 4, "wow": 4, "lot": 4, "breakdown": 4, "impress": 4, "huge": 4, "serious": 4, "is_json": 4, "myjson": 4, "valueerror": 4, "trial": 4, "elicit": 4, "wrangl": 4, "hoc": 4, "streamlin": 4, "subsequ": 4, "dataset": 4, "unwant": 4, "overflow": 4, "overwhelm": 4, "twitter": 4, "youtub": 4, "publish": 4, "schema": 4, "blueprint": 4, "nativ": 4, "json_format": 4, "person1": 4, "q1": 4, "person2": 4, "nest": 4, "todai": 4, "thellm": 4, "unend": 4, "whitespac": 4, "forget": 4, "throw": 4, "somewher": 4, "json_object": 4, "sheer": 4, "circul": 4, "vertex": 4, "worri": 4, "enum": 4, "refus": 4, "simpler": 4, "strongli": 4, "secextract": 4, "mentioned_ent": 4, "mentioned_plac": 4, "extract_from_sec_fil": 4, "sec_filing_text": 4, "hint": 4, "prompt_extract": 4, "sec_extract": 4, "washington": 4, "usabl": 4, "beg": 4, "with_structured_output": 4, "runnabl": 4, "typeddict": 4, "qu": 4, "langchain_openai": 4, "chatopenai": 4, "chatprompttempl": 4, "extract_from_sec_filing_langchain": 4, "structured_llm": 4, "from_messag": 4, "sec_extraction_langchain": 4, "hood": 4, "logit": 4, "willard": 4, "louf": 4, "reformul": 4, "finit": 4, "fsm": 4, "s_": 4, "sim": 4, "s_t": 4, "theta": 4, "s_1": 4, "v": 4, "mathbb": 4, "mask": 4, "tild": 4, "odot": 4, "rightarrow": 4, "boolean": 4, "wise": 4, "formul": 4, "regex": 4, "tran": 4, "thien": 4, "automaton": 4, "dfa": 4, "decod": 4, "outgo": 4, "renorm": 4, "yy": 4, "nn": 4, "ever": 4, "aa": 4, "lwai": 4, "prop": 4, "yynnaa": 4, "qwen": 4, "malform": 4, "sec_extraction_outlin": 4, "zsp": 4, "zicorp": 4, "phenomenon": 4, "popular": 4, "cpp": 4, "gbnf": 4, "ggml": 4, "bnf": 4, "ggerganov": 4, "accomplish": 4, "backu": 4, "naur": 4, "wikipedia": 4, "contributor": 4, "strictli": 4, "soon": 4, "curl": 4, "fssl": 4, "sh": 4, "extract_entities_from_sec_fil": 4, "suffix": 4, "ollama_structured_output_prompt_suffix": 4, "ollama_structured_output_temperatur": 4, "mistral": 4, "llama2": 4, "uncensor": 4, "model_json_schema": 4, "response_json": 4, "wrapper": 4, "exllama2": 4, "mlx": 4, "lm": 4, "medium": 4, "know": 4, "chanc": 4, "correctli": 4, "famili": 4, "furthermor": 4, "nonetheless": 4, "studi": 4, "wrap": 4, "gemma": 4, "uncov": 4, "wors": 4, "extran": 4, "dispar": 4, "preval": 4, "outdat": 4, "rapidli": 4, "fashion": 4, "remark": 4, "me": 4, "speak": 4, "freeli": 4, "aider": 4, "outweigh": 4, "rebutt": 4, "argu": 4, "reproduct": 4, "paint": 4, "pictur": 4, "verif": 4, "dottxt": 4, "flaw": 4, "uneven": 4, "didn": 4, "conflat": 4, "argument": 4, "drawback": 4, "unlock": 4, "wider": 4, "thank": 4, "pfiffer": 4, "aid24": 4, "dot24": 4, "sai": 4, "demo": 4, "tree": 4, "gge24": 4, "blob": 4, "readm": 4, "llf": 4, "xieyang": 4, "frederick": 4, "fiannaca": 4, "terri": 4, "koo": 4, "dixon": 4, "cai": 4, "ea": 4, "ny": 4, "usa": 4, "machineri": 4, "1145": 4, "3613905": 4, "3650756": 4, "ln": 4, "xuan": 4, "hai": 4, "nguyen": 4, "ngoc": 4, "tiviati": 4, "hieu": 4, "dao": 4, "shafiq": 4, "joti": 4, "kenji": 4, "kawaguchi": 4, "nanci": 4, "min": 4, "kan": 4, "2408": 4, "08656": 4, "out24": 4, "twt": 4, "zhi": 4, "cheng": 4, "kuang": 4, "tsai": 4, "chieh": 4, "hung": 4, "yun": 4, "nung": 4, "02442": 4, "tt24": 4, "vivien": 4, "vivien000": 4, "wl23": 4, "brandon": 4, "r\u00e9mi": 4, "2307": 4, "09702": 4, "wikipediacontributors24": 4, "wiktionari": 4, "naur_form": 4}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"introduct": [0, 1, 4], "content": [0, 2, 3, 4], "core": 0, "challeng": 0, "we": 0, "ll": 0, "address": 0, "A": [0, 1], "practic": [0, 1, 4], "approach": 0, "note": 0, "perspect": 0, "who": 0, "thi": 0, "book": 0, "i": 0, "For": 0, "outcom": 0, "prerequisit": 0, "set": 0, "up": 0, "your": 0, "environ": 0, "python": 0, "setup": 0, "api": [0, 4], "kei": [0, 2, 3], "configur": 0, "code": 0, "repositori": 0, "troubleshoot": 0, "common": 0, "issu": 0, "about": 0, "author": 0, "": 0, "tame": 1, "llm": [1, 2], "guid": 1, "pitfal": 1, "open": 1, "sourc": 1, "softwar": [1, 2], "chapter": 1, "1": [1, 3], "2": [1, 3], "wrestl": [1, 4], "structur": [1, 4], "output": [1, 3, 4], "3": [1, 3], "input": 1, "size": [1, 3], "length": [1, 3], "limit": [1, 3], "4": [1, 3], "5": 1, "The": [1, 2], "eval": [1, 2], "gap": [1, 2], "6": 1, "hallucin": 1, "realiti": 1, "7": 1, "safeti": 1, "concern": 1, "8": 1, "cost": [1, 3], "factor": 1, "9": 1, "break": 1, "free": 1, "from": 1, "cloud": 1, "provid": [1, 4], "appendix": 1, "tool": [1, 2, 4], "resourc": 1, "citat": 1, "non": 2, "determinist": 2, "gener": [2, 3], "machin": 2, "temperatur": 2, "sampl": 2, "spectrum": 2, "emerg": 2, "properti": 2, "problem": [2, 3, 4], "statement": [2, 3, 4], "tradit": 2, "v": 2, "design": 2, "applic": 2, "test": 2, "requir": 2, "matrix": 2, "conceptu": 2, "overview": 2, "consider": [2, 3], "metric": 2, "evalu": 2, "task": 2, "model": [2, 3], "base": [2, 3], "human": 2, "benchmark": 2, "leaderboard": 2, "lightev": 2, "mmlu": 2, "econometr": 2, "dataset": 2, "famili": 2, "us": 2, "langsmith": 2, "promptfoo": 2, "comparison": [2, 3, 4], "refer": [2, 3, 4], "what": 3, "ar": 3, "token": 3, "across": 3, "chunk": 3, "contextu": 3, "link": 3, "long": 3, "form": 3, "step": 3, "write": 3, "prompt": [3, 4], "templat": 3, "construct": 3, "dynam": 3, "paramet": 3, "report": 3, "exampl": 3, "usag": 3, "discuss": [3, 4], "implic": 3, "futur": 3, "conclus": [3, 4], "user": 4, "need": 4, "solut": 4, "strategi": 4, "techniqu": 4, "One": 4, "shot": 4, "specif": 4, "json": 4, "mode": 4, "langchain": 4, "outlin": 4, "ollama": 4, "compar": 4, "framework": 4, "best": 4, "research": 4, "ongo": 4, "debat": 4, "acknowledg": 4}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinxcontrib.bibtex": 9, "sphinx": 57}, "alltitles": {"Introduction": [[0, "introduction"], [4, "introduction"]], "Contents": [[0, "contents"], [2, "contents"], [3, "contents"], [4, "contents"]], "Core Challenges We\u2019ll Address": [[0, "core-challenges-we-ll-address"]], "A Practical Approach": [[0, "a-practical-approach"]], "A Note on Perspective": [[0, "a-note-on-perspective"]], "Who This Book Is For": [[0, "who-this-book-is-for"]], "Outcomes": [[0, "outcomes"]], "Prerequisites": [[0, "prerequisites"]], "Setting Up Your Environment": [[0, "setting-up-your-environment"]], "Python Environment Setup": [[0, "python-environment-setup"]], "API Keys Configuration": [[0, "api-keys-configuration"]], "Code Repository": [[0, "code-repository"]], "Troubleshooting Common Issues": [[0, "troubleshooting-common-issues"]], "About the Author(s)": [[0, "about-the-author-s"]], "Taming LLMs": [[1, "taming-llms"]], "A Practical Guide to LLM Pitfalls with Open Source Software": [[1, "a-practical-guide-to-llm-pitfalls-with-open-source-software"]], "Chapter 1: Introduction": [[1, "chapter-1-introduction"]], "Chapter 2: Wrestling with Structured Output": [[1, "chapter-2-wrestling-with-structured-output"]], "Chapter 3: Input Size and Length Limitations": [[1, "chapter-3-input-size-and-length-limitations"]], "Chapter 4: Output Size and Length Limitations": [[1, "chapter-4-output-size-and-length-limitations"]], "Chapter 5: The Evals Gap": [[1, "chapter-5-the-evals-gap"]], "Chapter 6: Hallucination: The Reality Gap": [[1, "chapter-6-hallucination-the-reality-gap"]], "Chapter 7: Safety Concerns": [[1, "chapter-7-safety-concerns"]], "Chapter 8: The Cost Factor": [[1, "chapter-8-the-cost-factor"]], "Chapter 9: Breaking Free from Cloud Providers": [[1, "chapter-9-breaking-free-from-cloud-providers"]], "Appendix A: Tools and Resources": [[1, "appendix-a-tools-and-resources"]], "Citation": [[1, "citation"]], "The Evals Gap": [[2, "the-evals-gap"]], "Non-Deterministic Generative Machines": [[2, "non-deterministic-generative-machines"]], "Temperature and Sampling": [[2, "temperature-and-sampling"]], "The Temperature Spectrum": [[2, "the-temperature-spectrum"]], "Emerging Properties": [[2, "emerging-properties"]], "Problem Statement": [[2, "problem-statement"], [3, "problem-statement"], [4, "problem-statement"]], "Evals of Traditional Software vs LLMs": [[2, "evals-table"]], "Evals Design": [[2, "evals-design"]], "LLM Application Testing Requirements Matrix": [[2, "validation-requirements"]], "Conceptual Overview": [[2, "conceptual-overview"]], "Design Considerations": [[2, "design-considerations"]], "Metrics": [[2, "metrics"]], "Key Metrics for Evaluating Generative Tasks": [[2, "key-metrics"]], "Evaluators": [[2, "evaluators"]], "Model-Based Evaluation": [[2, "model-based-evaluation"]], "Human-Based Evaluation": [[2, "human-based-evaluation"]], "Evaluating Evaluators": [[2, "evaluating-evaluators"]], "Benchmarks and Leaderboards": [[2, "benchmarks-and-leaderboards"]], "Tools": [[2, "tools"]], "LightEval": [[2, "lighteval"]], "MMLU Econometrics Task Dataset sample": [[2, "mmlu-econometrics"]], "Model Families Evaluated Using LightEval": [[2, "model-families"]], "LangSmith": [[2, "langsmith"]], "PromptFoo": [[2, "promptfoo"]], "Comparison": [[2, "comparison"]], "Comparison of Lighteval, LangSmith, and Promptfoo": [[2, "tool-comparison"]], "References": [[2, "references"], [3, "references"], [4, "references"]], "Output Size Limitations": [[3, "output-size-limitations"]], "What are Token Limits?": [[3, "what-are-token-limits"]], "Token Cost and Length Limitation Comparison Across Key Models": [[3, "token-cost-table"]], "Content Chunking with Contextual Linking": [[3, "content-chunking-with-contextual-linking"]], "Generating long-form content": [[3, "generating-long-form-content"]], "Step 1: Chunking the Content": [[3, "step-1-chunking-the-content"]], "Step 2: Writing the Base Prompt Template": [[3, "step-2-writing-the-base-prompt-template"]], "Step 3: Constructing Dynamic Prompt Parameters": [[3, "step-3-constructing-dynamic-prompt-parameters"]], "Step 4: Generating the Report": [[3, "step-4-generating-the-report"]], "Example Usage": [[3, "example-usage"]], "Discussion": [[3, "discussion"], [4, "discussion"]], "Implications": [[3, "implications"]], "Future Considerations": [[3, "future-considerations"]], "Conclusion": [[3, "conclusion"], [4, "conclusion"]], "Wrestling with Structured Output": [[4, "wrestling-with-structured-output"]], "User Needs": [[4, "user-needs"]], "Solutions": [[4, "solutions"]], "Strategies": [[4, "strategies"]], "Techniques and Tools": [[4, "techniques-and-tools"]], "One-Shot Prompts": [[4, "one-shot-prompts"]], "Structured Output with Provider-Specific APIs": [[4, "structured-output-with-provider-specific-apis"]], "JSON Mode": [[4, "json-mode"]], "LangChain": [[4, "langchain"]], "Outlines": [[4, "outlines"]], "Ollama": [[4, "ollama"]], "Comparing Solutions": [[4, "comparing-solutions"]], "Structured Output Frameworks Comparison": [[4, "structured-output-frameworks"]], "Best Practices": [[4, "best-practices"]], "Research and Ongoing Debate": [[4, "research-and-ongoing-debate"]], "Acknowledgements": [[4, "acknowledgements"]]}, "indexentries": {}}) \ No newline at end of file +Search.setIndex({"docnames": ["markdown/intro", "markdown/toc", "notebooks/evals", "notebooks/output_size_limit", "notebooks/structured_output"], "filenames": ["markdown/intro.md", "markdown/toc.md", "notebooks/evals.ipynb", "notebooks/output_size_limit.ipynb", "notebooks/structured_output.ipynb"], "titles": ["1. Introduction", "Taming LLMs", "4. The Evals Gap", "2. Output Size Limitations", "3. Wrestling with Structured Output"], "terms": {"am": 0, "alwai": [0, 2, 4], "do": [0, 2, 3, 4], "which": [0, 2, 3, 4], "cannot": [0, 2], "order": [0, 2, 4], "mai": [0, 2, 3, 4], "learn": [0, 2], "how": [0, 2, 3, 4], "pablo": [0, 2], "picasso": 0, "In": [0, 2, 3, 4], "recent": [0, 2, 4], "year": [0, 1, 2, 3, 4], "larg": [0, 1, 2, 3, 4], "languag": [0, 1, 2, 3, 4], "model": [0, 1, 4], "llm": [0, 3, 4], "have": [0, 2, 3, 4], "emerg": [0, 1, 4], "transform": [0, 2, 4], "forc": [0, 2, 4], "technologi": [0, 2, 3, 4], "promis": [0, 2], "revolution": 0, "build": [0, 1, 2, 3, 4], "product": [0, 1, 2, 4], "interact": [0, 2, 3, 4], "comput": [0, 2, 3, 4], "from": [0, 2, 3, 4], "chatgpt": [0, 4], "github": [0, 1, 2, 4], "copilot": 0, "claud": [0, 2, 3], "artifact": 0, "system": [0, 2, 3, 4], "captur": [0, 2], "public": [0, 2], "imagin": 0, "spark": 0, "gold": [0, 2], "rush": 0, "ai": [0, 2, 4], "power": [0, 1, 2, 3, 4], "applic": [0, 1, 3, 4], "howev": [0, 2, 3, 4], "beneath": 0, "surfac": [0, 2], "technolog": [0, 2], "revolut": 0, "li": [0, 2], "complex": [0, 2, 3, 4], "landscap": [0, 2], "practition": [0, 2], "must": [0, 2, 3], "navig": [0, 1, 2], "focus": [0, 2, 3, 4], "bring": 0, "awar": [0, 2, 3], "limit": [0, 2, 4], "har": [0, 1, 2, 3], "open": [0, 2, 3, 4], "sourc": [0, 2, 4], "solut": [0, 1, 2, 3], "overcom": [0, 2, 3], "them": [0, 2, 3, 4], "robust": [0, 2, 3, 4], "It": [0, 2, 3, 4], "offer": [0, 2, 3, 4], "critic": [0, 1, 2, 3, 4], "implement": [0, 1, 2, 3, 4], "back": [0, 2, 4], "reproduc": [0, 1, 2], "exampl": [0, 1, 2, 4], "while": [0, 1, 2, 3, 4], "mani": [0, 2, 3, 4], "resourc": [0, 2, 3], "cover": [0, 2, 3], "capabl": [0, 1, 2, 3, 4], "specif": [0, 1, 2, 3], "hidden": 0, "pitfal": 0, "engin": [0, 1, 2, 4], "technic": [0, 1, 2, 3, 4], "manag": [0, 1, 2, 3, 4], "face": [0, 2], "when": [0, 1, 2, 3, 4], "comprehens": [0, 1, 2, 3, 4], "guid": [0, 2, 4], "leverag": [0, 2, 3, 4], "battl": [0, 1], "test": [0, 1, 4], "tool": [0, 3], "throughout": [0, 2, 3, 4], "tackl": [0, 2], "follow": [0, 2, 3, 4], "non": [0, 1, 4], "exhaust": 0, "list": [0, 2, 3, 4], "structur": [0, 2, 3], "un": 0, "reliabl": [0, 2, 4], "struggl": [0, 2, 4], "maintain": [0, 2, 3, 4], "consist": [0, 2, 3, 4], "output": [0, 2], "format": [0, 2, 3, 4], "complic": 0, "integr": [0, 2, 4], "larger": [0, 2, 3, 4], "make": [0, 2, 3, 4], "error": [0, 2, 4], "handl": [0, 1, 2, 3, 4], "more": [0, 2, 3, 4], "size": [0, 2, 4], "length": [0, 2, 4], "constraint": [0, 1, 2, 3, 4], "strict": [0, 4], "token": [0, 1, 2, 4], "both": [0, 2], "input": [0, 2, 3, 4], "requir": [0, 3, 4], "care": [0, 2, 4], "chunk": [0, 1], "strategi": [0, 1, 2, 3], "long": [0, 1, 2, 4], "form": [0, 1, 2, 4], "effect": [0, 2, 3, 4], "tradit": 0, "softwar": [0, 4], "methodologi": [0, 2, 4], "break": [0, 2, 3], "down": [0, 2, 3], "deal": 0, "determinist": [0, 1, 4], "gener": [0, 1, 4], "new": [0, 2, 3, 4], "hallucin": [0, 2, 4], "These": [0, 2, 3, 4], "can": [0, 2, 3, 4], "plausibl": 0, "sound": 0, "entir": [0, 2, 3, 4], "fabric": [0, 2], "inform": [0, 2, 3, 4], "creat": [0, 2, 3, 4], "signific": [0, 2, 3, 4], "risk": [0, 2, 3], "safeti": [0, 2, 4], "secur": [0, 2, 3, 4], "harm": [0, 2], "bias": [0, 2, 4], "inappropri": 0, "safeguard": [0, 2], "monitor": [0, 1, 2], "ensur": [0, 2, 3, 4], "safe": [0, 2, 4], "deploy": [0, 1, 2, 4], "cost": [0, 2, 4], "optim": [0, 1, 2, 3], "The": [0, 3, 4], "financi": [0, 2, 3, 4], "oper": [0, 2, 3, 4], "base": [0, 1, 4], "quickli": [0, 3], "becom": [0, 2, 4], "prohibit": [0, 2], "without": [0, 2, 3, 4], "observ": [0, 2, 4], "vendor": [0, 1, 2], "lock": [0, 1], "cloud": [0, 2, 4], "provid": [0, 2, 3], "depend": [0, 2, 4], "through": [0, 1, 2, 3, 4], "proprietari": [0, 4], "infrastructur": 0, "difficult": [0, 2], "switch": 0, "self": [0, 1, 2], "host": [0, 1, 2], "take": [0, 1, 2, 3, 4], "hand": [0, 3, 4], "concret": [0, 1], "you": [0, 2, 3, 4], "run": [0, 2, 4], "modifi": [0, 2], "real": [0, 2, 3, 4], "world": [0, 2, 4], "scenario": [0, 2, 4], "best": [0, 1, 2], "techniqu": [0, 1, 2, 3], "pattern": [0, 1, 2, 4], "anti": [0, 2], "look": [0, 1, 2], "our": [0, 2, 3, 4], "goal": [0, 2, 3], "discourag": 0, "us": [0, 3, 4], "enabl": [0, 2, 3, 4], "By": [0, 1, 2, 3, 4], "understand": [0, 1, 2, 3, 4], "upfront": [0, 1], "better": [0, 1, 2, 3], "equip": [0, 1, 2], "avoid": [0, 2, 4], "current": [0, 1, 2, 3, 4], "discours": [0, 1], "around": [0, 1, 2, 3, 4], "tend": [0, 1, 2], "toward": [0, 2, 4], "extrem": [0, 2], "either": [0, 2, 3], "uncrit": 0, "enthusiasm": 0, "wholesal": [0, 2], "dismiss": 0, "differ": [0, 2, 3, 4], "focu": [0, 1, 2, 3, 4], "rather": [0, 2], "than": [0, 2], "theoret": 0, "examin": [0, 2, 3, 4], "first": [0, 2, 3, 4], "everi": [0, 2], "concept": [0, 2], "illustr": [0, 2, 3, 4], "execut": [0, 2], "immedi": [0, 2], "analysi": [0, 1, 2, 3], "balanc": [0, 2, 3, 4], "help": [0, 2, 3, 4], "reader": [0, 1], "decis": [0, 2, 4], "intend": [0, 2], "develop": [0, 2, 3, 4], "step": [0, 1, 2, 4], "insight": [0, 2, 3, 4], "along": [0, 2], "guidanc": [0, 4], "framework": [0, 2], "could": [0, 2, 3, 4], "derail": 0, "project": [0, 2], "earli": [0, 2, 4], "befor": [0, 2, 4], "thei": [0, 2, 3, 4], "costli": [0, 2], "problem": [0, 1], "too": [0, 2, 3], "late": 0, "lifecycl": 0, "design": [0, 1, 3, 4], "lead": [0, 2, 3, 4], "genai": 0, "initi": [0, 2, 3, 4], "leader": [0, 2], "architectur": [0, 2, 3, 4], "advoc": 0, "anyon": 0, "seek": [0, 2], "work": [0, 1, 2, 3, 4], "typic": [0, 2, 3, 4], "job": [0, 2], "role": [0, 2, 3, 4], "platform": [0, 2, 3, 4], "backend": [0, 2], "exist": [0, 2], "ml": 0, "transit": [0, 2, 3, 4], "overse": 0, "motiv": [0, 2, 4], "need": [0, 2, 3], "readi": [0, 2], "desir": [0, 2, 4], "perform": [0, 1, 2, 3, 4], "after": [0, 2, 3, 4], "read": [0, 2, 3, 4], "implic": [0, 1, 2], "experi": [0, 2, 3, 4], "recommend": [0, 2, 3, 4], "abl": [0, 2, 3, 4], "deploi": [0, 2, 3], "proper": [0, 4], "realist": 0, "effort": [0, 2, 4], "estim": [0, 2], "impact": [0, 2, 3, 4], "timelin": 0, "To": [0, 2, 3, 4], "most": [0, 2, 3, 4], "should": [0, 2, 3, 4], "basic": [0, 2, 3], "program": [0, 2], "knowledg": [0, 2], "introductori": [0, 1], "langchain": [0, 1, 2, 3], "e": [0, 2, 3, 4], "g": [0, 2, 3, 4], "chat": [0, 2, 3, 4], "prompt": [0, 1, 2], "templat": [0, 1, 2], "access": [0, 2, 3, 4], "openai": [0, 2, 4], "anthrop": [0, 4], "similar": [0, 2, 4], "grade": [0, 2], "dive": 0, "here": [0, 2, 3, 4], "get": [0, 2, 3, 4], "start": [0, 2, 4], "activ": [0, 2], "virtual": [0, 2], "m": [0, 2, 4], "venv": 0, "env": [0, 2, 3, 4], "bin": 0, "On": [0, 2, 4], "window": [0, 1, 2], "script": 0, "instal": [0, 2, 4], "packag": [0, 2, 4], "pip": [0, 2, 4], "r": [0, 2, 3, 4], "txt": [0, 2, 3, 4], "file": [0, 2, 3, 4], "root": 0, "directori": [0, 2], "add": [0, 2, 3], "other": [0, 2, 3, 4], "sensit": [0, 2], "openai_api_kei": 0, "your_openai_api_key_her": 0, "never": [0, 4], "share": [0, 2, 4], "commit": [0, 2], "version": [0, 2, 4], "control": [0, 2, 4], "contain": [0, 2, 3, 4], "kept": [0, 2], "privat": [0, 2], "clone": 0, "companion": 0, "git": 0, "http": [0, 1, 2, 3, 4], "com": [0, 1, 2, 3, 4], "souzatharsi": [0, 1], "tamingllm": [0, 1], "cd": 0, "If": [0, 2, 4], "encount": [0, 1, 2], "rate": [0, 2], "consid": [0, 2, 3, 4], "smaller": [0, 2, 3, 4], "retri": [0, 4], "logic": [0, 2, 3], "conflict": [0, 2], "try": [0, 2, 4], "fresh": 0, "like": [0, 2, 3, 4], "poetri": 0, "check": [0, 2, 4], "page": [0, 2], "known": [0, 2, 4], "now": [0, 2, 3, 4], "let": [0, 2, 3, 4], "begin": [0, 2, 4], "explor": [0, 2, 4], "dr": 0, "tharsi": [0, 1], "souza": [0, 1], "scientist": 0, "special": [0, 2, 4], "he": [0, 2], "lectur": 0, "columbia": 0, "univers": [0, 2], "master": [0, 4], "scienc": [0, 2], "appli": [0, 2, 3, 4], "analyt": 0, "head": [0, 2, 3], "equiti": [0, 2], "citadel": 0, "former": [0, 2], "senior": [0, 2], "vp": 0, "two": [0, 2, 3, 4], "sigma": 0, "invest": [0, 2, 4], "With": [0, 2], "over": [0, 1, 2, 3, 4], "15": [0, 2, 4], "deliv": [0, 2], "across": [0, 2, 4], "startup": 0, "fortun": 0, "500": [0, 2], "compani": [0, 2, 3, 4], "global": [0, 2], "also": [0, 2, 3, 4], "an": [0, 1, 2, 3, 4], "numer": [0, 2], "scholarli": 0, "frequent": [0, 2, 4], "speaker": [0, 2], "academ": [0, 2], "busi": [0, 2], "confer": [0, 4], "ground": [0, 1, 2], "background": [0, 2, 3], "draw": [0, 2, 4], "scale": [0, 2, 4], "stage": [0, 4], "major": [0, 2, 4], "institut": [0, 2], "well": [0, 2, 4], "advis": 0, "profit": [0, 2, 3, 4], "organ": [0, 2, 3], "contribut": [0, 2, 3], "uniqu": [0, 2], "bridg": 0, "gap": 0, "between": [0, 2, 3, 4], "potenti": [0, 2, 3, 4], "next": [0, 2, 4], "hold": [0, 2], "ph": 0, "d": [0, 2, 4], "ucl": 0, "london": 0, "phil": 0, "sc": 0, "b": [0, 2, 4], "abstract": [1, 2, 4], "heavili": [1, 2, 4], "gloss": 1, "fundament": [1, 2, 4], "challeng": [1, 2, 3, 4], "convers": [1, 2, 3, 4], "thi": [1, 2, 3, 4], "book": [1, 2], "kei": [1, 4], "python": [1, 2, 3, 4], "proven": 1, "yet": [1, 2, 3], "i": [1, 2, 3, 4], "unstructur": [1, 4], "context": [1, 2, 3, 4], "code": [1, 2, 4], "sidestep": 1, "inher": [1, 2, 3, 4], "core": [1, 2], "we": [1, 2, 3, 4], "ll": [1, 2], "address": [1, 2, 3, 4], "approach": [1, 2, 3, 4], "note": [1, 2, 3, 4], "perspect": 1, "who": [1, 2, 3, 4], "For": [1, 2, 3, 4], "outcom": [1, 2, 4], "prerequisit": 1, "set": [1, 2, 3, 4], "up": [1, 2, 3, 4], "your": [1, 2, 3, 4], "environ": [1, 2, 3, 4], "setup": [1, 2, 4], "api": [1, 2], "configur": [1, 2], "repositori": [1, 2], "troubleshoot": 1, "common": [1, 2, 3, 4], "issu": [1, 2, 3, 4], "about": [1, 2, 3, 4], "author": [1, 2, 4], "": [1, 2, 3, 4], "statement": 1, "One": [1, 2], "shot": [1, 2], "json": [1, 2, 3], "mode": 1, "outlin": [1, 2], "multipl": [1, 2, 3, 4], "choic": [1, 2, 4], "pydant": [1, 2, 4], "discuss": [1, 2], "compar": [1, 2, 3], "research": [1, 2, 3], "ongo": [1, 2], "debat": 1, "conclus": 1, "acknowledg": [1, 2], "refer": 1, "content": 1, "what": [1, 2, 4], "ar": [1, 2, 4], "contextu": [1, 2], "link": [1, 2], "write": [1, 2, 4], "construct": [1, 2, 4], "dynam": [1, 2], "paramet": [1, 2, 4], "report": [1, 2, 4], "usag": [1, 2, 4], "futur": [1, 2], "consider": [1, 4], "machin": [1, 4], "temperatur": [1, 2, 3, 4], "sampl": [1, 3, 4], "spectrum": [1, 2], "properti": 1, "conceptu": [1, 4], "overview": [1, 4], "compon": [1, 2], "metric": 1, "evalu": [1, 3, 4], "human": [1, 3, 4], "benchmark": 1, "leaderboard": 1, "type": [1, 2, 3, 4], "detect": [1, 2, 4], "retriev": [1, 2], "augment": [1, 2], "rag": 1, "select": [1, 2], "index": [1, 2, 3, 4], "vector": 1, "store": [1, 2, 3], "method": [1, 2, 3, 4], "pipelin": [1, 2, 4], "valid": [1, 2, 4], "guard": 1, "filter": [1, 2, 4], "sanit": 1, "alert": 1, "cach": [1, 2], "invalid": [1, 4], "predict": [1, 2, 4], "llama": [1, 2, 4], "llamafil": 1, "ollama": 1, "migrat": 1, "commun": [1, 2, 4], "misc": 1, "tharsistpsouza2024tamingllm": 1, "t": [1, 2, 3, 4], "p": [1, 2, 4], "titl": [1, 2], "2024": [1, 2, 3, 4], "journal": [1, 2, 4], "url": [1, 2, 4], "doesn": [2, 3, 4], "matter": 2, "beauti": 2, "theori": 2, "smart": 2, "agre": 2, "wrong": 2, "richard": 2, "feynman": 2, "advent": 2, "mark": 2, "pivot": 2, "shift": 2, "unlik": 2, "where": [2, 3, 4], "norm": 2, "introduc": [2, 3, 4], "realm": 2, "behavior": 2, "convent": 2, "paradigm": 2, "mere": 2, "evolut": 2, "conceiv": 2, "assess": [2, 3], "those": [2, 3, 4], "entrench": 2, "driven": 2, "seem": [2, 4], "daunt": 2, "ignor": 2, "chang": 2, "option": [2, 3, 4], "relianc": 2, "outdat": [2, 4], "fail": 2, "account": 2, "probabilist": 2, "natur": [2, 3, 4], "inevit": 2, "setback": 2, "imper": 2, "embrac": 2, "proactiv": 2, "mindset": 2, "involv": [2, 4], "front": 2, "foster": [2, 4], "cultur": 2, "continu": [2, 3, 4], "adapt": [2, 3], "same": [2, 3, 4], "produc": [2, 4], "novel": 2, "text": [2, 3, 4], "train": [2, 4], "data": [2, 3, 4], "respons": [2, 3, 4], "each": [2, 3, 4], "time": [2, 3, 4], "re": [2, 3, 4], "queri": 2, "even": [2, 3, 4], "ident": 2, "strength": 2, "ask": [2, 4], "question": [2, 4], "isn": 2, "bug": 2, "featur": [2, 4], "random": [2, 4], "allow": [2, 3, 4], "creativ": [2, 4], "divers": [2, 3, 4], "testabl": 2, "servic": [2, 3, 4], "advic": 2, "mean": [2, 3, 4], "yield": 2, "exceedingli": 2, "regulatori": 2, "complianc": [2, 4], "guarante": [2, 4], "user": [2, 3], "trust": [2, 4], "affect": 2, "inconsist": [2, 4], "primari": 2, "determin": [2, 3, 4], "come": [2, 3, 4], "dure": [2, 4], "calcul": 2, "probabl": [2, 4], "distribut": [2, 4], "nucleu": 2, "holtzman": 2, "et": [2, 4], "al": [2, 4], "2020": 2, "top": [2, 4], "k": [2, 3, 4], "coher": [2, 3], "simpl": [2, 3, 4], "singl": [2, 3, 4], "summari": [2, 4], "dramat": [2, 4], "alter": 2, "wai": [2, 3, 4], "systemat": [2, 4], "At": [2, 4], "0": [2, 3, 4], "rigid": 2, "1": [2, 4], "vari": 2, "less": 2, "2": [2, 4], "wildli": 2, "often": [2, 3, 4], "incoher": 2, "inadequ": 2, "dotenv": [2, 3, 4], "import": [2, 3, 4], "load_dotenv": [2, 3, 4], "o": [2, 3, 4], "load": [2, 3, 4], "variabl": [2, 3, 4], "panda": 2, "pd": 2, "def": [2, 3, 4], "generate_respons": 2, "model_nam": [2, 3], "str": [2, 3, 4], "float": [2, 3], "attempt": [2, 3], "int": [2, 3], "3": [2, 4], "datafram": 2, "demonstr": [2, 3, 4], "client": [2, 4], "result": [2, 3, 4], "temp": 2, "rang": [2, 3, 4], "complet": [2, 3, 4], "messag": [2, 4], "max_token": 2, "50": 2, "append": [2, 3, 4], "displai": [2, 4], "group": [2, 3], "df_result": 2, "print": [2, 3, 4], "f": [2, 3, 4], "ntemperatur": 2, "40": 2, "temp_respons": 2, "_": [2, 4], "row": 2, "iterrow": 2, "return": [2, 3, 4], "max_length": [2, 4], "10000": [2, 3, 4], "appl": [2, 3, 4], "sec_fil": [2, 4], "unit": [2, 3, 4], "state": [2, 3, 4], "nsecur": 2, "AND": [2, 4], "exchang": [2, 3, 4], "commiss": [2, 3, 4], "nwashington": 2, "c": [2, 4], "20549": 2, "n": [2, 3, 4], "nform": 2, "10": [2, 3, 4], "annual": 2, "pursuant": 2, "TO": 2, "section": [2, 3, 4], "13": 2, "OR": 2, "OF": 2, "THE": 2, "act": 2, "1934": 2, "nfor": 2, "fiscal": [2, 3], "end": [2, 3, 4], "septemb": [2, 3], "28": [2, 3], "nor": 2, "period": [2, 3], "ncommiss": 2, "number": [2, 3, 4], "001": 2, "36743": 2, "ng66145g66i43": 2, "jpg": 2, "nappl": 2, "inc": [2, 3, 4], "exact": 2, "name": [2, 3, 4], "registr": 2, "specifi": [2, 3, 4], "its": [2, 3, 4], "charter": 2, "ncalifornia": 2, "t94": 2, "2404110": 2, "jurisdict": 2, "nof": 2, "incorpor": 2, "employ": 2, "identif": 2, "No": [2, 4], "none": 2, "park": 2, "ncupertino": 2, "california": [2, 4], "n95014": 2, "princip": 2, "offic": 2, "zip": 2, "408": 2, "996": 2, "1010": 2, "telephon": 2, "includ": [2, 3, 4], "area": [2, 4], "regist": 2, "12": [2, 3], "ntitl": 2, "class": [2, 3, 4], "ttrade": 2, "symbol": 2, "tname": 2, "ncommon": 2, "stock": [2, 4], "00001": 2, "par": 2, "valu": [2, 3, 4], "per": [2, 3], "naapl": 2, "tthe": 2, "nasdaq": [2, 4], "market": [2, 3, 4], "llc": [2, 4], "n0": 2, "000": [2, 4], "due": [2, 3], "2025": 2, "875": 2, "n1": 2, "625": 2, "2026": 2, "n2": 2, "2027": 2, "375": 2, "2029": 2, "n3": 2, "050": 2, "2031": 2, "600": 2, "2042": 2, "nindic": 2, "season": 2, "issuer": 2, "defin": [2, 3, 4], "rule": [2, 3, 4], "405": 2, "nye": 2, "whether": [2, 3, 4], "ha": [2, 4], "all": [2, 3, 4], "preced": 2, "month": 2, "shorter": 2, "wa": [2, 4], "been": 2, "subject": 2, "past": 2, "90": 2, "dai": [2, 4], "submit": 2, "electron": 2, "regul": [2, 4], "232": 2, "chapter": 2, "acceler": 2, "filer": 2, "growth": 2, "see": [2, 4], "definit": [2, 4], "12b": 2, "nlarg": 2, "tacceler": 2, "nnon": 2, "tsmaller": 2, "nemerg": 2, "nif": 2, "indic": [2, 4], "elect": 2, "extend": [2, 4], "compli": [2, 4], "ani": [2, 3, 4], "revis": 2, "standard": 2, "attest": 2, "intern": 2, "under": [2, 4], "404": 2, "sarban": 2, "oxlei": 2, "u": [2, 4], "7262": 2, "firm": 2, "prepar": [2, 3], "audit": 2, "reflect": 2, "correct": [2, 4], "previous": [2, 3, 4], "restat": 2, "recoveri": 2, "incent": 2, "compens": 2, "receiv": [2, 3, 4], "relev": 2, "240": 2, "10d": 2, "shell": 2, "nthe": 2, "aggreg": 2, "vote": 2, "held": [2, 4], "affili": [2, 4], "march": [2, 4], "29": [2, 4], "last": [2, 3, 4], "second": [2, 3], "quarter": 2, "approxim": [2, 4], "628": [2, 4], "553": [2, 4], "sole": 2, "purpos": [2, 4], "disclosur": 2, "director": 2, "date": [2, 4], "exclud": 2, "becaus": 2, "person": [2, 4], "deem": 2, "necessarili": 2, "n15": 2, "115": [2, 4], "823": [2, 4], "were": [2, 4], "outstand": [2, 4], "octob": [2, 4], "18": [2, 4], "ndocument": 2, "BY": 2, "nportion": 2, "proxi": 2, "relat": 2, "meet": [2, 4], "sharehold": 2, "part": [2, 3, 4], "iii": 2, "within": [2, 3, 4], "120": 2, "ntabl": 2, "npage": 2, "npart": 2, "nitem": 2, "nbusi": 2, "1a": 2, "nrisk": 2, "factor": [2, 3, 4], "n5": 2, "1b": 2, "nunresolv": 2, "staff": 2, "comment": 2, "n17": 2, "1c": 2, "ncybersecur": 2, "nproperti": 2, "n18": 2, "nlegal": 2, "proceed": 2, "4": [2, 4], "nmine": 2, "ii": [2, 4], "5": [2, 3, 4], "nmarket": 2, "stockhold": 2, "purchas": 2, "n19": 2, "6": [2, 3, 4], "reserv": 2, "n20": 2, "7": [2, 3], "nmanag": 2, "condit": 2, "n21": 2, "7a": 2, "nquantit": 2, "qualit": 2, "n27": 2, "8": [2, 3], "nfinanci": 2, "supplementari": 2, "n28": 2, "9": 2, "nchang": 2, "disagr": 2, "n51": 2, "9a": 2, "ncontrol": 2, "procedur": 2, "9b": 2, "nother": 2, "n52": 2, "9c": 2, "ndisclosur": 2, "regard": 2, "foreign": 2, "prevent": [2, 4], "inspect": 2, "ndirector": 2, "corpor": 2, "govern": 2, "11": 2, "nexecut": 2, "ownership": 2, "certain": [2, 3, 4], "benefici": 2, "owner": 2, "ncertain": 2, "relationship": 2, "transact": 2, "independ": [2, 4], "14": [2, 4], "nprincip": 2, "fee": 2, "iv": 2, "nexhibit": 2, "schedul": 2, "n53": 2, "16": 2, "n56": 2, "nthi": 2, "forward": 2, "litig": 2, "reform": 2, "1995": 2, "uncertainti": 2, "locat": 2, "item": 2, "expect": [2, 3, 4], "event": 2, "assumpt": 2, "doe": [2, 3, 4], "directli": [2, 4], "histor": 2, "fact": 2, "macroeconom": 2, "identifi": [2, 3, 4], "word": [2, 3, 4], "anticip": 2, "believ": [2, 4], "plan": [2, 4], "would": [2, 3, 4], "term": [2, 3], "actual": [2, 3, 4], "significantli": [2, 3], "might": [2, 3, 4], "caus": 2, "assum": [2, 3], "oblig": [2, 3], "updat": [2, 3, 4], "reason": [2, 3, 4], "except": [2, 4], "law": 2, "nunless": 2, "otherwis": 2, "present": [2, 3, 4], "herein": 2, "calendar": 2, "particular": [2, 4], "associ": [2, 3, 4], "collect": [2, 3], "wholli": 2, "own": [2, 3], "subsidiari": 2, "unless": 2, "ncompani": 2, "manufactur": 2, "smartphon": 2, "tablet": 2, "wearabl": [2, 4], "accessori": 2, "sell": 2, "varieti": 2, "52": 2, "53": 2, "week": 2, "saturdai": 2, "nproduct": 2, "niphon": 2, "line": 2, "io": [2, 4], "iphon": [2, 4], "pro": [2, 3], "se": 2, "nmac": 2, "maco": 2, "mac": [2, 4], "laptop": 2, "macbook": 2, "air": 2, "desktop": 2, "imac": 2, "mini": [2, 3, 4], "studio": 2, "nipad": 2, "multipurpos": 2, "ipado": 2, "ipad": [2, 4], "nwearabl": 2, "home": 2, "smartwatch": 2, "wireless": 2, "headphon": 2, "spatial": 2, "watcho": 2, "watch": 2, "ultra": 2, "seri": 2, "airpod": 2, "max": 2, "beat": 2, "vision": 2, "visiono": 2, "nhome": 2, "tv": 2, "media": 2, "stream": [2, 4], "game": 2, "devic": [2, 4], "tvo": 2, "homepod": 2, "high": [2, 3, 4], "fidel": [2, 4], "naccessori": 2, "brand": 2, "third": 2, "parti": 2, "nservic": 2, "nadvertis": 2, "advertis": 2, "licens": 2, "arrang": 2, "napplecar": 2, "portfolio": [2, 4], "support": [2, 4], "applecar": 2, "prioriti": 2, "network": [2, 4], "repair": 2, "replac": 2, "case": [2, 3, 4], "addit": [2, 3, 4], "coverag": 2, "instanc": [2, 3], "accident": 2, "damag": 2, "theft": 2, "loss": 2, "countri": 2, "ncloud": 2, "keep": [2, 3], "custom": 2, "avail": [2, 3, 4], "ndigit": 2, "variou": [2, 3, 4], "app": 2, "discov": 2, "download": 2, "digit": 2, "music": 2, "video": 2, "podcast": 2, "subscript": 2, "arcad": 2, "fit": [2, 3, 4], "sm": 2, "curat": 2, "listen": 2, "demand": [2, 4], "radio": 2, "station": 2, "magazin": 2, "exclus": 2, "origin": [2, 3, 4], "live": 2, "sport": 2, "npayment": 2, "payment": 2, "card": 2, "co": 2, "credit": 2, "pai": 2, "cashless": 2, "nsegment": 2, "primarili": 2, "geograph": 2, "basi": 2, "segment": [2, 3, 4], "america": 2, "europ": 2, "greater": 2, "china": 2, "japan": 2, "rest": 2, "asia": 2, "pacif": 2, "north": 2, "south": 2, "european": 2, "india": 2, "middl": 2, "east": 2, "africa": 2, "mainland": 2, "hong": 2, "kong": 2, "taiwan": 2, "australia": 2, "asian": 2, "although": 2, "hardwar": 2, "one": [2, 3, 4], "separ": [2, 3], "align": [2, 3, 4], "partner": 2, "region": 2, "consum": [2, 4], "small": [2, 4], "mid": [2, 3], "educ": [2, 3], "enterpris": [2, 4], "resel": 2, "retail": 2, "onlin": 2, "direct": 2, "sale": 2, "emploi": [2, 4], "indirect": 2, "channel": 2, "cellular": 2, "carrier": 2, "net": [2, 4], "38": 2, "62": 2, "respect": 2, "total": [2, 3, 4], "ncompetit": 2, "highli": [2, 4], "competit": 2, "character": 2, "aggress": 2, "price": 2, "downward": 2, "pressur": 2, "gross": 2, "margin": [2, 4], "short": [2, 3, 4], "life": 2, "cycl": 2, "evolv": [2, 3], "industri": [2, 4], "improv": [2, 3, 4], "characterist": 2, "rapid": 2, "adopt": [2, 4], "advanc": [2, 3, 4], "competitor": 2, "compet": 2, "veri": 2, "low": [2, 4], "imit": 2, "infring": 2, "intellectu": 2, "abil": [2, 4], "successfulli": [2, 4], "innov": [2, 3], "marketplac": 2, "nearli": 2, "rel": 2, "qualiti": [2, 3, 4], "strong": [2, 4], "ecosystem": 2, "reput": 2, "expand": 2, "opportun": 2, "substanti": 2, "establish": 2, "some": [2, 3, 4], "broader": 2, "lower": [2, 4], "particularli": [2, 3, 4], "intens": [2, 4], "cut": [2, 3], "littl": 2, "free": 2, "illegitim": 2, "obtain": [2, 4], "collabor": 2, "nsuppli": 2, "nalthough": 2, "essenti": [2, 3, 4], "particip": 2, "therefor": 2, "wide": [2, 3, 4], "shortag": 2, "commod": 2, "fluctuat": 2, "commonli": 2, "util": [2, 3], "onli": [2, 3, 4], "capac": 2, "until": [2, 4], "supplier": 2, "matur": 2, "increas": [2, 3, 4], "accept": 2, "decid": [2, 3], "concentr": 2, "instead": [2, 3, 4], "enter": 2, "agreement": 2, "suppli": [2, 4], "renew": 2, "nresearch": 2, "nbecaus": 2, "upon": [2, 3], "flow": [2, 3], "enhanc": [2, 3, 4], "acquisit": 2, "nintellectu": 2, "broad": [2, 4], "right": 2, "aspect": [2, 3, 4], "patent": 2, "copyright": 2, "trademark": 2, "trade": [2, 4], "secret": 2, "differenti": 2, "success": [2, 4], "reli": 2, "skill": 2, "personnel": 2, "regularli": 2, "protect": 2, "aris": 2, "pursu": 2, "thousand": 2, "accumul": 2, "durat": 2, "adequ": 2, "nin": 2, "necessari": [2, 3], "process": [2, 3, 4], "commerci": [2, 4], "experienc": 2, "higher": 2, "holidai": 2, "addition": 2, "expens": 2, "fill": 2, "inventori": 2, "launch": 2, "older": 2, "declin": 2, "newer": 2, "distributor": 2, "nhuman": 2, "capit": [2, 3, 4], "peopl": 2, "plai": [2, 4], "strive": 2, "attract": 2, "retain": [2, 3], "talent": 2, "inclus": [2, 3, 4], "team": [2, 4], "member": 2, "so": [2, 4], "As": [2, 3, 4], "had": 2, "164": 2, "full": [2, 3, 4], "equival": 2, "employe": 2, "ncompens": 2, "benefit": [2, 4], "equit": 2, "recogn": 2, "thrive": [2, 4], "succe": 2, "profession": [2, 4], "health": 2, "awai": 2, "ngrowth": 2, "achiev": [2, 4], "career": 2, "leadership": 2, "influenc": [2, 4], "advantag": [2, 3, 4], "being": 2, "nworkplac": 2, "practic": [2, 3], "polici": 2, "equal": 2, "workplac": 2, "harass": 2, "discrimin": 2, "ninclus": 2, "sustain": 2, "workforc": 2, "repres": [2, 4], "serv": [2, 3, 4], "represent": [2, 3], "level": [2, 3, 4], "nengag": 2, "honest": 2, "among": 2, "everyon": 2, "grow": [2, 4], "encourag": [2, 4], "feedback": [2, 4], "concern": 2, "conduct": 2, "survei": [2, 4], "gaug": 2, "sentiment": [2, 4], "nhealth": 2, "everywher": 2, "measur": 2, "mitig": [2, 3, 4], "possibl": [2, 4], "hazard": 2, "crisi": 2, "put": 2, "place": [2, 4], "visitor": 2, "navail": 2, "quarterli": 2, "q": 2, "amend": 2, "sec": [2, 3, 4], "Such": 2, "charg": 2, "investor": [2, 4], "default": [2, 4], "aspx": 2, "websit": 2, "www": 2, "press": 2, "releas": [2, 4], "environment": 2, "social": 2, "detail": [2, 3, 4], "referenc": 2, "further": [2, 3, 4], "inact": 2, "textual": 2, "unknown": 2, "describ": 2, "below": [2, 3, 4], "materi": [2, 4], "advers": 2, "trend": [2, 4], "conjunct": 2, "consolid": 2, "accompani": 2, "nmacroeconom": 2, "econom": 2, "outsid": 2, "chain": [2, 3], "facil": 2, "assembli": 2, "site": 2, "nadvers": 2, "slow": 2, "recess": 2, "unemploy": 2, "inflat": 2, "tighter": 2, "interest": [2, 3, 4], "currenc": 2, "confid": [2, 4], "spend": 2, "monetari": 2, "volatil": 2, "incom": 2, "asset": 2, "contract": 2, "logist": 2, "instabl": 2, "inabl": 2, "financ": 2, "insolv": 2, "failur": 2, "deriv": 2, "counterparti": 2, "debt": 2, "reduc": [2, 3, 4], "liquid": [2, 3], "fair": 2, "instrument": 2, "polit": 2, "disput": 2, "geopolit": 2, "tension": 2, "terror": 2, "disast": 2, "accid": 2, "interrupt": 2, "npolit": 2, "whole": 2, "outsourc": 2, "korea": 2, "vietnam": 2, "restrict": [2, 4], "tariff": 2, "export": 2, "good": [2, 4], "portion": 2, "revenu": [2, 3, 4], "raw": [2, 4], "go": [2, 3, 4], "action": [2, 3], "restructur": 2, "ceas": 2, "accord": [2, 4], "disrupt": [2, 3], "announc": 2, "notic": [2, 4], "led": [2, 4], "escal": [2, 3], "sever": [2, 3, 4], "nmani": 2, "prone": 2, "earthquak": 2, "climat": 2, "weather": 2, "occur": 2, "fire": 2, "nuclear": 2, "plant": 2, "terrorist": 2, "attack": 2, "hostil": 2, "ransomwar": 2, "cybersecur": 2, "labor": 2, "beyond": 2, "nsuch": 2, "imposs": 2, "delai": 2, "ineffici": 2, "slowdown": 2, "outag": 2, "neg": [2, 4], "seriou": 2, "injuri": 2, "pandem": 2, "covid": 2, "19": 2, "economi": 2, "imposit": 2, "stringent": 2, "travel": 2, "freight": 2, "movement": 2, "ramp": 2, "nfollow": 2, "expenditur": 2, "resum": 2, "lose": 2, "exacerb": 2, "consequ": [2, 4], "insur": 2, "insuffici": 2, "nglobal": 2, "unabl": 2, "There": [2, 3, 4], "assur": 2, "contrast": 2, "minor": 2, "overal": [2, 3, 4], "naddition": 2, "intensifi": 2, "seamlessli": [2, 3], "function": [2, 3, 4], "nto": 2, "remain": [2, 3], "stimul": 2, "ndue": 2, "upgrad": 2, "appropri": [2, 3, 4], "quantiti": 2, "defect": 2, "defici": 2, "supersed": 2, "nsubstanti": 2, "much": 2, "transport": 2, "diminish": 2, "flexibl": [2, 3, 4], "respond": 2, "provis": 2, "reimburs": 2, "warranti": 2, "out": [2, 3, 4], "unanticip": 2, "liabil": 2, "adher": [2, 3, 4], "violat": 2, "final": [2, 3, 4], "finish": 2, "destin": 2, "man": 2, "made": [2, 3, 4], "prepay": 2, "termin": 2, "recover": 2, "exposur": 2, "nfutur": 2, "suffici": [2, 4], "semiconductor": 2, "suffer": 2, "poor": 2, "constrain": [2, 3, 4], "shipment": 2, "altern": [2, 3], "sophist": [2, 3], "unexpectedli": 2, "interfer": 2, "unsaf": 2, "artifici": 2, "intellig": 2, "expos": 2, "inaccur": [2, 4], "fix": [2, 3], "widespread": 2, "vulner": 2, "exploit": 2, "compromis": 2, "claim": 2, "recal": 2, "modif": 2, "off": [2, 3, 4], "intang": 2, "fine": [2, 4], "lost": [2, 3], "cancel": 2, "record": 2, "obsolet": 2, "exce": 2, "realiz": 2, "accru": 2, "excess": 2, "review": [2, 4], "impair": 2, "whenev": 2, "circumst": 2, "amount": [2, 3, 4], "carri": [2, 4], "incur": 2, "given": [2, 3, 4], "unpredict": [2, 4], "pace": 2, "obsolesc": 2, "forecast": 2, "150": 2, "incorrectli": [2, 4], "fulli": [2, 3], "extens": [2, 3, 4], "issuanc": 2, "unknowingli": 2, "notifi": 2, "preclud": 2, "choos": 2, "bui": 2, "percept": 2, "android": 2, "playstat": 2, "nintendo": 2, "xbox": 2, "posit": [2, 3, 4], "inclin": 2, "devot": 2, "compel": [2, 4], "dissatisfi": 2, "vast": 2, "legal": 2, "storefront": 2, "mechan": [2, 4], "safari": 2, "union": 2, "eu": 2, "dma": 2, "interfac": 2, "reduct": 2, "narrow": 2, "scope": [2, 3], "elimin": 2, "nfailur": 2, "appeal": 2, "subscrib": 2, "nsome": 2, "manner": [2, 3, 4], "nurtur": 2, "distinct": 2, "nmuch": 2, "chief": 2, "especi": [2, 3, 4], "silicon": 2, "vallei": 2, "constantli": 2, "driver": 2, "recruit": 2, "subsidi": 2, "staf": 2, "contractor": 2, "placement": 2, "increment": 2, "weaken": 2, "stop": [2, 3], "telecommun": 2, "war": 2, "virus": 2, "physic": 2, "ins": 2, "incid": 2, "redund": 2, "ineffect": 2, "eventu": 2, "thing": [2, 4], "interf": 2, "imped": 2, "ship": 2, "nloss": 2, "unauthor": 2, "confidenti": 2, "encrypt": 2, "But": [2, 4], "absolut": [2, 4], "malici": 2, "behalf": 2, "gain": 2, "regular": [2, 4], "normal": [2, 4], "investig": 2, "penalti": 2, "judgment": 2, "against": 2, "frequenc": [2, 3], "actor": 2, "circumv": [2, 3], "remov": 2, "obfusc": 2, "forens": 2, "evid": [2, 4], "hinder": [2, 4], "recov": 2, "perpetr": 2, "target": [2, 4], "profil": 2, "authent": 2, "hack": 2, "malfeas": 2, "faulti": 2, "password": 2, "irregular": 2, "fraudul": 2, "induc": 2, "disclos": [2, 3, 4], "usernam": 2, "turn": 2, "multifactor": 2, "unusu": 2, "freez": 2, "suspici": 2, "nwhile": 2, "ninvest": 2, "contempl": 2, "endeavor": 2, "distract": 2, "tangibl": 2, "approv": 2, "oner": 2, "ventur": 2, "riski": 2, "pose": [2, 3, 4], "leas": 2, "unfavor": 2, "arisen": 2, "ordinari": 2, "cours": 2, "resolv": 2, "sometim": [2, 4], "indemnif": 2, "indemnifi": 2, "alleg": 2, "magnitud": 2, "assert": 2, "royalti": 2, "vigor": 2, "defend": 2, "court": 2, "internation": 2, "plaintiff": 2, "injunct": 2, "relief": 2, "nregardless": 2, "merit": 2, "recognit": 2, "settl": 2, "uncertain": 2, "abov": 2, "disgorg": 2, "remedi": 2, "worldwid": 2, "antitrust": 2, "privaci": [2, 4], "local": [2, 3, 4], "bill": 2, "commerc": 2, "internet": 2, "mobil": [2, 4], "televis": 2, "film": 2, "anticorrupt": 2, "cash": [2, 3], "repatri": 2, "monei": 2, "launder": 2, "tax": 2, "wast": 2, "recycl": 2, "ncomplianc": 2, "impos": [2, 4], "interpret": 2, "ethic": 2, "agent": 2, "found": [2, 4], "nregulatori": 2, "satisfi": 2, "ban": 2, "nexpect": 2, "stakehold": 2, "increasingli": [2, 4], "greenhous": 2, "ga": 2, "emiss": 2, "civil": 2, "disagre": 2, "perceiv": 2, "feder": 2, "scrutini": 2, "nfrom": 2, "taken": [2, 4], "engag": [2, 4], "noncompli": 2, "individu": [2, 3], "lawsuit": 2, "monopol": 2, "nfurther": 2, "earn": 2, "googl": [2, 4], "search": 2, "nthere": 2, "connect": [2, 4], "retent": 2, "transfer": 2, "pass": [2, 4], "pend": 2, "inquiri": 2, "government": 2, "entiti": [2, 4], "biometr": 2, "breach": 2, "notif": 2, "permit": [2, 4], "healthcar": 2, "liabl": 2, "investigatori": 2, "cardhold": 2, "compress": [2, 3], "acquir": 2, "mix": [2, 4], "extent": 2, "unexpect": [2, 4], "dollar": 2, "denomin": 2, "rais": [2, 3], "offset": 2, "strengthen": 2, "nconvers": 2, "therebi": [2, 3], "thu": 2, "hedg": 2, "deterior": 2, "sovereign": 2, "heighten": 2, "worsen": 2, "A": [2, 3, 4], "collater": 2, "bank": 2, "unsecur": 2, "subassembli": 2, "assembl": 2, "few": [2, 3, 4], "legisl": 2, "ireland": 2, "singapor": 2, "organis": 2, "propos": 2, "modern": [2, 3, 4], "minimum": 2, "statutori": 2, "valuat": 2, "defer": 2, "bodi": 2, "likelihood": 2, "adequaci": 2, "ultim": 2, "ow": 2, "ngener": 2, "volum": [2, 3], "unrel": 2, "averag": [2, 4], "repurchas": 2, "point": [2, 3], "dividend": 2, "consumm": 2, "declar": 2, "board": 2, "unresolv": 2, "nnone": 2, "threat": 2, "dedic": [2, 4], "postur": 2, "25": 2, "sinc": [2, 3, 4], "2016": 2, "coordin": 2, "assist": [2, 4], "log": 2, "track": 2, "committe": 2, "oversight": 2, "counsel": 2, "chair": 2, "substanc": 2, "17": 2, "headquart": 2, "cupertino": [2, 4], "land": 2, "center": [2, 4], "suitabl": 2, "formal": [2, 4], "articl": [2, 3], "promot": 2, "conclud": 2, "uninstal": 2, "web": 2, "browser": 2, "screen": 2, "june": 2, "24": [2, 4], "preliminari": 2, "find": [2, 3, 4], "contractu": 2, "desist": 2, "stai": [2, 3], "grant": 2, "ndepart": 2, "justic": 2, "21": 2, "depart": 2, "doj": 2, "district": 2, "attornei": 2, "jersei": 2, "redress": 2, "anticompetit": 2, "nonmonetari": 2, "defens": 2, "itself": 2, "nepic": 2, "epic": 2, "northern": 2, "unfair": 2, "guidelin": 2, "enjoin": 2, "extern": 2, "januari": 2, "motion": 2, "enforc": [2, 4], "oppos": 2, "30": 2, "vacat": 2, "fourth": 2, "did": [2, 4], "mine": 2, "nnot": 2, "aapl": 2, "nholder": 2, "na": 2, "23": 2, "301": 2, "npurchas": 2, "nshare": 2, "three": 2, "million": 2, "nperiod": 2, "ttotal": 2, "taverag": 2, "npaid": 2, "publicli": [2, 4], "nannounc": 2, "napproxim": 2, "That": [2, 4], "Be": 2, "nunder": 2, "njune": 2, "august": 2, "nopen": 2, "negoti": 2, "t35": 2, "697": 2, "t224": 2, "naugust": 2, "31": 2, "t42": 2, "910": 2, "t221": 2, "39": 2, "nseptemb": 2, "t33": 2, "653": 2, "t222": 2, "86": 2, "ntotal": 2, "t112": 2, "260": 2, "t89": 2, "074": 2, "110": 2, "billion": 2, "20": [2, 4], "previou": [2, 3, 4], "2023": [2, 4], "10b5": 2, "graph": 2, "show": [2, 3, 4], "five": 2, "cumul": 2, "reinvest": 2, "dow": 2, "jone": 2, "supersector": 2, "100": [2, 4], "close": 2, "27": 2, "2019": 2, "n2218": 2, "tseptemb": 2, "2021": 2, "2022": 2, "t100": 2, "t207": 2, "t273": 2, "t281": 2, "t322": 2, "t430": 2, "t113": 2, "t156": 2, "t131": 2, "t155": 2, "t210": 2, "ndow": 2, "t146": 2, "t216": 2, "t215": 2, "nfirst": 2, "nsecond": 2, "nthird": 2, "sequoia": 2, "nfourth": 2, "plu": 2, "nfiscal": 2, "six": 2, "realign": 2, "span": 2, "wherea": 2, "indirectli": 2, "tabl": [2, 3, 4], "n2024": 2, "tchang": 2, "t2023": 2, "t2022": 2, "namerica": 2, "t167": 2, "045": 2, "t3": 2, "t162": 2, "560": 2, "t169": 2, "658": 2, "neurop": 2, "t101": 2, "328": 2, "t7": 2, "294": 2, "t95": 2, "118": 2, "ngreater": 2, "t66": 2, "952": 2, "t72": 2, "559": 2, "t74": 2, "200": 2, "njapan": 2, "t25": 2, "052": 2, "t24": 2, "257": 2, "977": 2, "nrest": 2, "t30": 2, "t4": 2, "t29": 2, "615": 2, "t1": 2, "t391": 2, "035": 2, "t2": 2, "t383": 2, "285": 2, "t394": 2, "decreas": 2, "weak": 2, "renminbi": 2, "yen": [2, 4], "22": 2, "categori": 2, "t201": 2, "183": 2, "t200": 2, "583": 2, "t205": 2, "489": 2, "984": 2, "357": 2, "t40": 2, "177": 2, "t26": 2, "694": 2, "t28": 2, "300": [2, 3], "292": 2, "t37": 2, "005": 2, "t39": 2, "845": 2, "t41": 2, "241": 2, "n96": 2, "169": 2, "t13": 2, "t85": 2, "t9": 2, "t78": 2, "129": 2, "amort": 2, "bundl": 2, "flat": 2, "entri": 2, "partial": [2, 3], "ngross": 2, "percentag": 2, "t109": 2, "633": 2, "t108": 2, "803": 2, "t114": 2, "728": 2, "t71": 2, "t60": 2, "345": 2, "t56": 2, "054": 2, "t180": 2, "683": 2, "148": 2, "t170": 2, "782": 2, "t36": 2, "t73": 2, "t70": 2, "t46": 2, "t44": 2, "t43": 2, "save": [2, 3], "noper": 2, "t31": 2, "370": 2, "t5": 2, "915": 2, "t14": 2, "251": 2, "npercentag": 2, "t8": 2, "nsell": 2, "administr": 2, "097": 2, "932": 2, "094": 2, "t6": 2, "t57": 2, "467": 2, "t54": 2, "847": 2, "t51": 2, "t15": 2, "headcount": 2, "nprovis": 2, "749": 2, "t16": 2, "741": 2, "t19": 2, "neffect": 2, "nstatutori": 2, "t21": 2, "aid": 2, "nliquid": 2, "unrestrict": 2, "140": 2, "ndebt": 2, "97": 2, "payabl": 2, "promissori": 2, "paper": [2, 4], "nleas": 2, "space": 2, "nmanufactur": 2, "noncancel": 2, "ndeem": 2, "2017": 2, "tcja": 2, "paid": 2, "nstate": 2, "fund": 2, "escrow": 2, "ncapit": 2, "95": 2, "nrecent": 2, "pronounc": 2, "nincom": 2, "decemb": 2, "fasb": 2, "asu": 2, "09": [2, 3], "topic": [2, 3, 4], "740": 2, "reconcili": 2, "reconcil": [2, 4], "quantit": 2, "threshold": 2, "disaggreg": 2, "prospect": 2, "novemb": 2, "07": [2, 3, 4], "280": 2, "maker": 2, "codm": 2, "alloc": 2, "retrospect": 2, "ncritic": 2, "conform": [2, 4], "principl": 2, "gaap": 2, "nuncertain": 2, "domest": 2, "taxat": 2, "adjust": [2, 3, 4], "resolut": 2, "conting": 2, "26": 2, "still": 2, "ninterest": 2, "forth": 2, "hypothet": 2, "nsensit": 2, "nhypothet": 2, "nrate": 2, "npotenti": 2, "n100": 2, "tenor": 2, "ndeclin": 2, "755": 2, "089": 2, "nterm": 2, "nincreas": 2, "t139": 2, "t194": 2, "nforeign": 2, "express": [2, 4], "var": 2, "mont": 2, "carlo": 2, "simul": [2, 4], "maximum": [2, 3], "interv": 2, "538": 2, "669": 2, "underli": [2, 4], "nindex": 2, "tpage": 2, "nconsolid": 2, "n29": 2, "n30": 2, "sheet": 2, "n31": 2, "n32": 2, "n33": 2, "nnote": 2, "n34": 2, "nreport": 2, "n48": 2, "nall": 2, "omit": [2, 4], "submiss": 2, "nyear": 2, "n2023": 2, "n2022": 2, "nnet": 2, "t294": 2, "866": 2, "t298": 2, "085": 2, "t316": 2, "199": 2, "t96": 2, "ncost": 2, "t185": 2, "233": 2, "t189": 2, "282": 2, "471": 2, "119": 2, "855": 2, "t22": 2, "075": 2, "352": 2, "t214": 2, "137": 2, "t223": 2, "546": 2, "t123": 2, "216": 2, "t119": 2, "437": 2, "t269": 2, "565": 2, "334": 2, "485": 2, "736": 2, "103": 2, "t93": 2, "995": 2, "t99": 2, "nearn": 2, "nbasic": 2, "ndilut": 2, "08": [2, 4], "343": 2, "783": 2, "744": 2, "231": 2, "215": 2, "963": 2, "095": 2, "812": 2, "547": 2, "325": 2, "819": 2, "nsee": 2, "translat": 2, "t395": 2, "765": 2, "511": 2, "unreal": 2, "832": 2, "t323": 2, "212": 2, "nadjust": 2, "337": 2, "717": 2, "394": 2, "138": 2, "850": 2, "563": 2, "104": 2, "t204": 2, "t253": 2, "816": 2, "899": 2, "272": 2, "t98": 2, "016": 2, "652": 2, "t88": 2, "531": 2, "nasset": 2, "ncurrent": 2, "ncash": 2, "943": 2, "965": 2, "228": 2, "590": 2, "naccount": 2, "410": 2, "508": 2, "nvendor": 2, "t32": 2, "833": 2, "477": 2, "ninventori": 2, "286": 2, "331": 2, "287": 2, "695": 2, "t152": 2, "987": 2, "t143": 2, "566": 2, "t91": 2, "479": 2, "544": 2, "t45": 2, "680": 2, "715": 2, "834": 2, "t64": 2, "758": 2, "t211": 2, "993": 2, "t209": 2, "017": 2, "t364": 2, "980": 2, "t352": 2, "nliabil": 2, "t68": 2, "960": 2, "t62": 2, "611": 2, "304": 2, "t58": 2, "829": 2, "ndefer": 2, "249": 2, "061": 2, "ncommerci": 2, "967": 2, "985": 2, "t10": 2, "912": 2, "822": 2, "t176": 2, "392": 2, "t145": 2, "308": 2, "750": 2, "281": 2, "888": 2, "t49": 2, "848": 2, "638": 2, "t308": 2, "030": 2, "t290": 2, "ncommit": 2, "nsharehold": 2, "400": 2, "116": 2, "786": 2, "550": 2, "n83": 2, "276": 2, "naccumul": 2, "deficit": 2, "154": 2, "214": 2, "172": 2, "452": 2, "950": 2, "146": 2, "t50": 2, "672": 2, "t63": 2, "090": 2, "nbegin": 2, "849": 2, "365": 2, "423": 2, "346": 2, "175": 2, "withheld": 2, "settlement": 2, "award": 2, "521": 2, "971": 2, "t12": 2, "034": 2, "t11": 2, "nend": 2, "t83": 2, "nretain": 2, "068": 2, "562": 2, "ndividend": 2, "218": 2, "793": 2, "612": 2, "099": 2, "454": 2, "846": 2, "77": 2, "046": 2, "186": 2, "109": 2, "t163": 2, "rsu": 2, "t0": 2, "98": 2, "94": 2, "32": 2, "737": 2, "929": 2, "ndepreci": 2, "445": 2, "519": 2, "688": 2, "038": 2, "266": 2, "227": 2, "006": 2, "788": 2, "356": 2, "271": 2, "520": 2, "618": 2, "484": 2, "731": 2, "684": 2, "499": 2, "020": 2, "889": 2, "448": 2, "552": 2, "031": 2, "t118": 2, "254": 2, "t110": 2, "543": 2, "t122": 2, "151": 2, "48": 2, "656": 2, "513": 2, "76": 2, "923": 2, "nproce": 2, "211": 2, "686": 2, "917": 2, "135": 2, "828": 2, "446": 2, "447": 2, "959": 2, "708": 2, "086": 2, "935": 2, "705": 2, "354": 2, "nfinanc": 2, "441": 2, "431": 2, "223": 2, "234": 2, "025": 2, "841": 2, "nrepurchas": 2, "949": 2, "89": 2, "402": 2, "465": 2, "nrepay": 2, "958": 2, "repay": 2, "978": 2, "955": 2, "361": 2, "581": 2, "160": 2, "121": 2, "983": 2, "108": 2, "488": 2, "794": 2, "760": 2, "nsupplement": 2, "102": 2, "t18": 2, "679": 2, "573": 2, "33": 2, "nbasi": 2, "prior": 2, "reclassifi": 2, "nrevenu": 2, "remit": 2, "straight": 2, "vest": 2, "treat": 2, "sold": 2, "nderiv": 2, "combin": [2, 3, 4], "nonleas": 2, "34": 2, "entitl": 2, "reward": 2, "commenc": 2, "deliveri": 2, "stand": 2, "alon": 2, "ssp": 2, "object": [2, 4], "icloud": 2, "siri": 2, "map": [2, 4], "discount": 2, "lack": [2, 4], "undeliv": 2, "unbil": 2, "accordingli": 2, "n26": 2, "n37": 2, "35": 2, "proport": 2, "moder": 2, "64": 2, "dilut": 2, "nnumer": 2, "ndenomin": 2, "nweight": 2, "312": 2, "316": 2, "856": 2, "antidilut": 2, "tunreal": 2, "ngain": 2, "tfair": 2, "nvalu": 2, "tcash": 2, "nequival": 2, "tcurrent": 2, "tnon": 2, "t27": 2, "nlevel": 2, "nmonei": 2, "t778": 2, "nmutual": 2, "n515": 2, "t105": 2, "t617": 2, "nsubtot": 2, "293": 2, "395": 2, "nu": 2, "treasuri": 2, "516": 2, "t212": 2, "087": 2, "380": 2, "agenc": 2, "159": 2, "t703": 2, "t17": 2, "568": 2, "158": 2, "810": 2, "ncertif": 2, "deposit": 2, "t873": 2, "t387": 2, "t478": 2, "066": 2, "ncorpor": 2, "t65": 2, "622": 2, "t270": 2, "953": 2, "939": 2, "027": 2, "t47": 2, "886": 2, "nmunicip": 2, "t412": 2, "t405": 2, "t190": 2, "nmortgag": 2, "595": 2, "t175": 2, "403": 2, "t23": 2, "367": 2, "278": 2, "t132": 2, "t583": 2, "635": 2, "t128": 2, "056": 2, "966": 2, "t34": 2, "t160": 2, "t688": 2, "650": 2, "36": 2, "359": 2, "t481": 2, "n442": 2, "t428": 2, "t923": 2, "t909": 2, "406": 2, "114": 2, "468": 2, "136": 2, "t271": 2, "533": 2, "048": 2, "491": 2, "332": 2, "t320": 2, "t608": 2, "t76": 2, "840": 2, "956": 2, "890": 2, "t20": 2, "627": 2, "243": 2, "t628": 2, "t602": 2, "t192": 2, "t410": 2, "735": 2, "636": 2, "t344": 2, "t144": 2, "470": 2, "657": 2, "831": 2, "125": 2, "162": 2, "t173": 2, "752": 2, "quot": 2, "corrobor": 2, "mortgag": 2, "classifi": 2, "37": 2, "cross": 2, "swap": 2, "remeasur": 2, "notion": 2, "069": 2, "730": 2, "575": 2, "493": 2, "t104": 2, "777": 2, "nhedg": 2, "433": 2, "505": 2, "247": 2, "ntrade": 2, "41": 2, "44": 2, "depreci": 2, "nland": 2, "690": 2, "nmachineri": 2, "t80": 2, "205": 2, "314": 2, "nleasehold": 2, "839": 2, "128": 2, "599": 2, "73": 2, "70": 2, "884": 2, "852": 2, "t55": 2, "335": 2, "906": 2, "601": 2, "703": 2, "010": 2, "457": 2, "634": 2, "391": 2, "neuropean": 2, "opinion": 2, "1991": 2, "2007": 2, "irish": 2, "branch": 2, "2003": 2, "2014": 2, "2015": 2, "request": [2, 3, 4], "minist": 2, "juli": 2, "annul": 2, "ecj": 2, "hear": 2, "asid": 2, "confirm": 2, "via": [2, 4], "unrecogn": 2, "nfeder": 2, "571": 2, "080": 2, "644": 2, "265": 2, "801": 2, "726": 2, "570": 2, "298": 2, "49": 2, "t84": 2, "428": 2, "603": 2, "483": 2, "t347": 2, "t669": 2, "076": 2, "830": 2, "419": 2, "072": 2, "pretax": 2, "72": 2, "71": 2, "ncomput": 2, "885": 2, "012": 2, "124": 2, "518": 2, "nimpact": 2, "n10": 2, "246": 2, "311": 2, "366": 2, "397": 2, "153": 2, "nexcess": 2, "893": 2, "871": 2, "192": 2, "739": 2, "ntax": 2, "carryforward": 2, "302": 2, "naccru": 2, "413": 2, "421": 2, "nunreal": 2, "173": 2, "168": 2, "873": 2, "743": 2, "nless": 2, "374": 2, "007": 2, "369": 2, "551": 2, "998": 2, "nright": 2, "179": 2, "nminimum": 2, "674": 2, "940": 2, "t511": 2, "t455": 2, "t490": 2, "805": 2, "202": 2, "indefinit": 2, "temporari": 2, "727": 2, "044": 2, "284": 2, "ndecreas": 2, "386": 2, "463": 2, "982": 2, "542": 2, "936": 2, "070": 2, "expir": 2, "statut": 2, "229": 2, "494": 2, "closur": 2, "intercompani": 2, "exceed": 2, "multiyear": 2, "exercis": 2, "noncash": 2, "rou": 2, "tfinanci": 2, "t2024": 2, "tother": 2, "661": 2, "tproperti": 2, "015": 2, "303": 2, "676": 2, "t165": 2, "t752": 2, "t859": 2, "430": 2, "842": 2, "tfinanc": 2, "n2025": 2, "820": 2, "t171": 2, "991": 2, "n2026": 2, "914": 2, "n2027": 2, "t59": 2, "733": 2, "n2028": 2, "360": 2, "t38": 2, "398": 2, "n2029": 2, "187": 2, "nthereaft": 2, "t837": 2, "undiscount": 2, "790": 2, "imput": 2, "376": 2, "534": 2, "t896": 2, "weight": 2, "borrow": 2, "implicit": 2, "readili": 2, "42": 2, "proce": 2, "nine": 2, "00": 2, "nmatur": 2, "333": 2, "264": 2, "948": 2, "645": 2, "309": 2, "arrear": 2, "namount": 2, "n2013": 2, "nfix": 2, "2062": 2, "t97": 2, "341": 2, "03": 2, "65": 2, "t106": 2, "572": 2, "n97": 2, "nunamort": 2, "premium": 2, "321": 2, "358": 2, "113": 2, "662": 2, "convert": [2, 4], "930": 2, "342": 2, "800": 2, "180": 2, "43": 2, "88": 2, "ndure": 2, "425": 2, "426": 2, "372": 2, "589": 2, "055": 2, "appreci": 2, "four": 2, "holder": 2, "n2014": 2, "bonu": 2, "nrestrict": 2, "nnumber": 2, "nrsu": 2, "ngrant": 2, "naggreg": 2, "nfair": 2, "nbalanc": 2, "t240": 2, "427": 2, "t75": 2, "t150": 2, "861": 2, "501": 2, "768": 2, "87": 2, "101": 2, "878": 2, "144": 2, "t127": 2, "t135": 2, "91": 2, "456": 2, "78": 2, "59": 2, "t140": 2, "80": 2, "326": 2, "t158": 2, "204": 2, "350": 2, "002": [2, 3], "nuncondit": 2, "uncondit": 2, "206": 2, "440": 2, "156": 2, "t633": 2, "t670": 2, "226": 2, "45": 2, "nconting": 2, "least": 2, "accrual": 2, "nconcentr": 2, "attribut": [2, 4], "46": 2, "t67": 2, "098": 2, "082": 2, "062": 2, "569": 2, "895": 2, "458": 2, "207": 2, "nonrecur": 2, "t142": 2, "196": 2, "t138": 2, "t147": 2, "859": 2, "nchina": 2, "n66": 2, "t181": 2, "887": 2, "t172": 2, "269": 2, "nlong": 2, "664": 2, "n4": 2, "797": 2, "778": 2, "219": 2, "47": 2, "nopinion": 2, "nwe": 2, "fairli": 2, "pcaob": 2, "criteria": 2, "sponsor": 2, "treadwai": 2, "2013": 2, "unqualifi": 2, "thereon": 2, "nthese": 2, "misstat": 2, "fraud": 2, "ndescript": 2, "naudit": 2, "nhow": 2, "nmatter": 2, "qualifi": 2, "letter": 2, "advisor": 2, "ernst": 2, "young": 2, "llp": 2, "auditor": 2, "2009": 2, "nsan": 2, "jose": 2, "nnovemb": 2, "coso": 2, "nour": 2, "ndefinit": 2, "pertain": 2, "mainten": 2, "accur": [2, 4], "disposit": 2, "receipt": 2, "degre": 2, "nevalu": 2, "nbase": 2, "supervis": 2, "13a": 2, "15d": 2, "summar": [2, 3], "ninher": 2, "met": 2, "appear": [2, 4], "paragraph": 2, "51": [2, 4], "ninsid": 2, "deirdr": 2, "brien": 2, "vice": 2, "presid": 2, "affirm": 2, "april": 2, "withhold": 2, "remitt": 2, "jeff": 2, "william": 2, "mr": 2, "insid": 2, "copi": [2, 3], "exhibit": 2, "solicit": 2, "document": [2, 3, 4], "id": 2, "00042": 2, "nincorpor": 2, "texhibit": 2, "descript": [2, 4], "tform": 2, "tfile": 2, "nrestat": 2, "n8": 2, "namend": 2, "bylaw": 2, "nindentur": 2, "york": [2, 4], "mellon": 2, "truste": 2, "noffic": 2, "certif": 2, "2018": 2, "85": 2, "2043": 2, "05": 2, "2044": 2, "februari": 2, "55": 2, "2045": 2, "900": 2, "700": 2, "60": 2, "250": 2, "2036": 2, "2046": 2, "450": 2, "2047": 2, "2049": 2, "2030": 2, "2050": 2, "2060": 2, "2028": 2, "2041": 2, "2051": 2, "2061": 2, "2032": 2, "2052": 2, "54": 2, "2033": 2, "2053": 2, "n9": 2, "ceo": 2, "n12": 2, "nsubsidiari": 2, "n23": 2, "nconsent": 2, "n24": 2, "npower": 2, "signatur": 2, "nrule": 2, "nsection": 2, "1350": 2, "n101": 2, "ninlin": 2, "xbrl": 2, "n104": 2, "inlin": 2, "compensatori": 2, "herewith": 2, "furnish": 2, "herebi": 2, "undertak": 2, "56": 2, "nsignatur": 2, "npursuant": 2, "duli": 2, "sign": 2, "undersign": 2, "thereunto": 2, "ndate": 2, "nby": 2, "luca": [2, 4], "maestri": 2, "nluca": 2, "nsenior": 2, "nchief": 2, "nknow": 2, "THESE": 2, "whose": 2, "constitut": 2, "appoint": 2, "timothi": 2, "cook": 2, "jointli": 2, "hi": [2, 4], "her": 2, "substitut": 2, "him": 2, "thereto": 2, "therewith": 2, "ratifi": 2, "said": 2, "done": [2, 4], "virtu": 2, "hereof": 2, "nname": 2, "ttitl": 2, "tdate": 2, "tchief": 2, "tnovemb": 2, "ntimothi": 2, "tsenior": 2, "chri": 2, "kondo": 2, "nchri": 2, "wanda": 2, "austin": 2, "nwanda": 2, "alex": 2, "gorski": 2, "tdirector": 2, "nalex": 2, "andrea": 2, "jung": 2, "nandrea": 2, "arthur": 2, "levinson": 2, "narthur": 2, "monica": 2, "lozano": 2, "nmonica": 2, "ronald": 2, "sugar": 2, "nronald": 2, "susan": 2, "l": 2, "wagner": 2, "nsusan": 2, "57": 2, "gpt": [2, 3, 4], "turbo": [2, 3, 4], "invdestacksmeticsisdict": 2, "setispect": 2, "20cyan": 2, "evaluationseld": 2, "anvis": 2, "droitent": 2, "discernminerv": 2, "versbobprefvers": 2, "vo\u8be5": 2, "option\u548c": 2, "meio": 2, "\u0432\u0440\u0435\u043ccisco": 2, "dellaischenpoihscap": 2, "geme": 2, "gettim": 2, "unscal": 2, "score": [2, 4], "vocabulari": [2, 4], "closer": 2, "sharpen": 2, "uniform": 2, "raschka": 2, "repetit": [2, 3, 4], "radic": 2, "grappl": 2, "safer": 2, "don": [2, 3, 4], "highlight": [2, 3, 4], "anoth": 2, "fascin": 2, "spontan": 2, "answer": [2, 3, 4], "aren": 2, "explicitli": 2, "pre": 2, "fig": [2, 3, 4], "linear": 2, "absent": 2, "simpli": [2, 3, 4], "coax": 2, "onc": [2, 3], "reach": [2, 3, 4], "journei": 2, "suddenli": 2, "manifest": 2, "call": [2, 3, 4], "phase": 2, "stark": 2, "deliber": 2, "wei": 2, "stabl": 2, "suit": 2, "contend": 2, "7b": 2, "70b": 2, "rethink": 2, "math": 2, "tutor": 2, "children": 2, "verifi": [2, 4], "just": [2, 3, 4], "predefin": [2, 4], "explan": [2, 4], "child": 2, "ag": 2, "bound": 2, "weren": 2, "accuraci": [2, 4], "kind": 2, "dimens": 2, "explicit": [2, 4], "usual": 2, "precis": [2, 4], "resist": 2, "straightforward": [2, 3, 4], "quantif": 2, "contamin": 2, "carefulli": [2, 4], "craft": [2, 4], "massiv": 2, "alreadi": 2, "seen": 2, "memor": 2, "truli": 2, "unseen": 2, "rigor": 2, "longitudin": 2, "autom": [2, 4], "annot": 2, "mostli": [2, 4], "versu": 2, "latter": 2, "foundat": [2, 3], "tailor": 2, "solv": [2, 4], "great": [2, 4], "cognit": 2, "meta": [2, 3], "why": [2, 4], "misinform": 2, "factual": 2, "databas": [2, 4], "citat": 2, "tempor": 2, "scientif": 2, "fals": [2, 4], "manipul": 2, "medic": 2, "disclaim": 2, "referr": 2, "boundari": 2, "situat": [2, 3], "incorrect": 2, "expertis": 2, "bia": [2, 4], "gender": 2, "racial": 2, "demograph": 2, "stereotyp": 2, "reinforc": 2, "societ": 2, "pii": 2, "anonym": 2, "leakag": 2, "carryov": 2, "protocol": 2, "multi": [2, 4], "mathemat": 2, "fallaci": 2, "causal": 2, "edg": 2, "think": 2, "idiom": 2, "sarcasm": 2, "terminologi": 2, "lingual": 2, "misunderstand": 2, "syntax": 2, "scan": 2, "compat": [2, 4], "stabil": 2, "effici": [2, 3, 4], "scalabl": [2, 3], "overconfid": 2, "clariti": [2, 3, 4], "audienc": 2, "densiti": 2, "satisfact": [2, 4], "misus": 2, "moral": 2, "transpar": [2, 4], "co2": 2, "energi": 2, "consumpt": 2, "server": [2, 4], "batch": 2, "infer": 2, "imag": 2, "audio": 2, "etc": [2, 4], "truth": [2, 4], "layer": [2, 3, 4], "palm": 2, "shown": 2, "quantifi": 2, "rank": 2, "easi": [2, 3], "synthet": [2, 4], "post": [2, 4], "timeout": 2, "variat": 2, "maxim": 2, "inter": 2, "rater": 2, "priorit": 2, "ti": 2, "tier": 2, "holist": 2, "built": [2, 4], "mind": 2, "x": 2, "fast": [2, 4], "experiment": [2, 4], "iter": [2, 3, 4], "vi": 2, "later": [2, 4], "categor": [2, 4], "intrins": 2, "extrins": 2, "sequenc": [2, 4], "perplex": 2, "downstream": [2, 4], "valuabl": [2, 4], "distinguish": 2, "classif": [2, 4], "true": [2, 3, 4], "synthesi": 2, "discret": 2, "f1": 2, "match": [2, 4], "prefix": 2, "roug": 2, "bleu": 2, "charact": [2, 3, 4], "gram": 2, "bilingu": 2, "understudi": 2, "overlap": [2, 3], "favor": [2, 4], "breviti": 2, "insensit": 2, "semant": [2, 3], "orient": 2, "gist": 2, "sentenc": [2, 3, 4], "meteor": 2, "synonym": 2, "stem": [2, 4], "paraphras": 2, "alongsid": 2, "computation": [2, 3], "cider": 2, "consensu": 2, "tf": 2, "idf": 2, "caption": 2, "reliant": 2, "corpu": 2, "statist": 2, "ter": 2, "edit": 2, "hypothesi": 2, "penal": 2, "bertscor": 2, "embed": [2, 3], "bert": 2, "spice": 2, "proposit": 2, "scene": 2, "emphasi": 2, "pure": 2, "analyst": [2, 3], "dictionari": [2, 4], "rouge_1": 2, "rouge_2": 2, "ideal": [2, 4], "expert": [2, 3, 4], "cheaper": 2, "4o": [2, 3, 4], "evaluate_summari": 2, "unigram": 2, "bigram": 2, "huggingfac": 2, "librari": [2, 3, 4], "absl": 2, "py": 2, "rouge_scor": 2, "generated_summari": 2, "reference_summari": 2, "arg": [2, 3, 4], "dict": [2, 3, 4], "google_bleu": 2, "bleu_scor": 2, "rouge1": 2, "rouge2": 2, "arbitrari": 2, "chosen": 2, "sentence1": 2, "cat": 2, "sat": 2, "mat": 2, "sentence2": 2, "ate": 2, "3333333333333333": 2, "7272727272727272": 2, "4444444444444445": 2, "generate_summari": 2, "summir": 2, "correspond": [2, 4], "liner": 2, "excerpt": 2, "evaluate_summary_model": 2, "model_benchmark": 2, "models_test": 2, "benchmark_summari": 2, "model_summari": 2, "evaluation_result": 2, "reveal": 2, "analyz": [2, 3, 4], "statu": 2, "concis": 2, "element": [2, 4], "Its": 2, "verbos": 2, "peripher": 2, "quit": [2, 4], "overli": [2, 4], "simplifi": [2, 4], "miss": 2, "convei": [2, 3], "breadth": 2, "Of": 2, "vibe": 2, "visualize_prompt_comparison": 2, "visual": 2, "matplotlib": 2, "radar": 2, "plot": 2, "radar_plot": 2, "tmp": 2, "ipykernel_1652501": 2, "940173201": 2, "userwarn": 2, "figurecanvasagg": 2, "closest": 2, "largest": 2, "deviat": [2, 4], "suggest": [2, 4], "mention": [2, 4], "nuanc": [2, 3, 4], "granular": [2, 3], "fall": 2, "judg": 2, "themselv": 2, "main": [2, 3, 4], "instruct": [2, 3, 4], "tune": [2, 4], "assign": [2, 4], "likert": 2, "style": 2, "pairwis": 2, "ensembl": 2, "repeatedli": 2, "domain": 2, "clear": [2, 4], "fluenci": 2, "refin": 2, "excel": [2, 4], "narr": 2, "mirror": 2, "similarli": 2, "notabl": [2, 4], "properli": [2, 4], "henc": 2, "worth": 2, "integ": 2, "rubric": 2, "hollist": 2, "judgeevalu": 2, "grammar": [2, 4], "evaluate_with_llm": 2, "candid": 2, "pars": [2, 4], "criterion": 2, "basemodel": [2, 4], "judge_model": 2, "candidate_summari": 2, "written": 2, "grammat": 2, "y": [2, 4], "z": 2, "w": [2, 3], "beta": [2, 4], "response_format": [2, 4], "Then": 2, "benchmark_model": 2, "test_model": 2, "input_text": [2, 3], "tupl": 2, "trillion": [2, 4], "evals_list": 2, "1775618912": 2, "variant": 2, "slightli": 2, "drift": 2, "lowest": 2, "drop": 2, "gradient": 2, "visibl": 2, "degrad": [2, 4], "firstli": 2, "overhead": 2, "neglect": 2, "prefer": [2, 4], "egocentr": 2, "tight": 2, "field": [2, 4], "aproach": 2, "workflow": [2, 4], "assessor": 2, "aplic": 2, "aim": [2, 3, 4], "clearli": [2, 4], "earlier": 2, "depict": [2, 4], "correl": 2, "multilingu": 2, "golden": 2, "languang": 2, "arena": 2, "blind": 2, "randomli": 2, "pair": 2, "loop": 2, "customiz": 2, "irrelev": 2, "unhelp": 2, "though": [2, 4], "occasion": 2, "rare": 2, "inaccuraci": 2, "perfectli": 2, "cater": 2, "critiqu": 2, "elo": 2, "democrat": [2, 4], "thought": [2, 4], "exam": 2, "probe": 2, "certifi": 2, "histori": 2, "move": [2, 3], "began": 2, "glue": 2, "wang": 2, "entail": 2, "baselin": 2, "superglu": 2, "deeper": [2, 3], "successor": 2, "grew": 2, "big": 2, "bench": 2, "srivastava": 2, "arithmet": 2, "truthfulqa": 2, "lin": [2, 4], "decept": 2, "multitask": 2, "hendryck": 2, "multidisciplinari": 2, "stanford": 2, "helm": 2, "liang": 2, "multidimension": 2, "surround": [2, 4], "emphas": [2, 4], "humanev": 2, "chen": [2, 4], "lmsy": 2, "brought": 2, "dialogu": 2, "len": [2, 3], "replic": [2, 4], "chatbot": 2, "chiang": 2, "gather": 2, "alpacaev": 2, "duboi": 2, "mt": 2, "zheng": 2, "Their": [2, 4], "render": 2, "crowdsourc": 2, "livebench": 2, "white": 2, "resili": 2, "meaningfulli": 2, "monthli": 2, "zebralog": 2, "grid": 2, "puzzl": 2, "brailsford": 2, "1999": 2, "lsat": 2, "hous": 2, "clue": 2, "strateg": [2, 4], "deduct": 2, "arriv": 2, "programmat": [2, 4], "2x2": 2, "6x6": 2, "reductio": 2, "ad": [2, 4], "absurdum": 2, "sonnet": [2, 3], "hard": 2, "10b": 2, "counterfactu": 2, "composit": 2, "came": 2, "arc": 2, "prize": 2, "chollet": 2, "mike": 2, "knoop": 2, "founder": 2, "zapier": 2, "fran\u00e7oi": 2, "creator": 2, "agi": 2, "kera": 2, "meaning": [2, 3, 4], "genuin": 2, "old": 2, "possess": 2, "count": [2, 3], "elementari": 2, "novelti": 2, "someth": 2, "wouldn": 2, "interpol": 2, "memori": [2, 3], "synthes": 2, "fly": 2, "brute": 2, "minim": [2, 4], "pixel": 2, "perfect": 2, "color": 2, "unbeaten": 2, "win": 2, "deep": [2, 4], "poorli": 2, "recombin": 2, "spur": 2, "art": 2, "takeawai": 2, "algorithm": 2, "fourrier": 2, "lightweight": [2, 4], "bespok": 2, "sdk": 2, "cli": 2, "extract": [2, 3, 4], "autoregress": 2, "sub": 2, "liter": 2, "disturb": 2, "zero": [2, 4], "varianc": 2, "yt": 2, "ut": 2, "suppos": [2, 4], "exactli": [2, 4], "ol": 2, "heteroscedast": 2, "regress": 2, "wish": 2, "lag": 2, "bivari": 2, "evaluation_track": 2, "evaluationtrack": 2, "model_config": 2, "basemodelconfig": 2, "parallelismmanag": 2, "pipelineparamet": 2, "envconfig": 2, "is_accelerate_avail": 2, "datetim": 2, "timedelta": 2, "initprocessgroupkwarg": 2, "create_evaluation_pipelin": 2, "output_dir": 2, "cache_dir": 2, "pretrain": 2, "dtype": 2, "float16": 2, "max_sampl": 2, "kwargs_handl": 2, "3000": 2, "els": [2, 3], "save_detail": 2, "push_to_hub": 2, "pipeline_param": 2, "launcher_typ": 2, "env_config": 2, "override_batch_s": 2, "use_chat_templ": 2, "trust_remote_cod": 2, "pipeline_paramet": 2, "schemat": [2, 3], "vllm": [2, 4], "tgi": 2, "instanti": 2, "storag": 2, "push": 2, "hub": 2, "parallel": 2, "num_few_shot": 2, "automat": 2, "string": [2, 4], "vertic": 2, "bar": 2, "binari": 2, "flag": 2, "bigbench": 2, "winogrand": 2, "hellaswag": 2, "nlp": 2, "save_and_push_result": 2, "show_result": 2, "model_arg": 2, "remot": 2, "send": [2, 4], "serverless": 2, "inference_server_address": 2, "inference_server_auth": 2, "model_id": 2, "null": 2, "bash": 2, "command": 2, "model_config_path": 2, "path": [2, 3], "endpoint_model": 2, "yaml": [2, 4], "llama3": [2, 3], "qwen2": [2, 4], "smollm2": 2, "3b": 2, "alibaba": [2, 4], "5b": [2, 4], "hui": 2, "yang": 2, "compact": 2, "360m": 2, "allal": 2, "cluster": 2, "noteworthi": 2, "superior": 2, "grain": [2, 4], "salt": [2, 4], "give": 2, "exponenti": 2, "hug": 2, "modular": 2, "visit": 2, "offici": 2, "revisit": 2, "rememb": 2, "api_kei": [2, 3], "trace": 2, "langchain_tracing_v2": 2, "langchain_api_kei": 2, "hf_evalu": 2, "langsmith_evalu": 2, "ls_client": 2, "dataset_nam": 2, "create_dataset": 2, "create_exampl": 2, "dataset_id": 2, "calculate_scor": 2, "reference_output": 2, "oai_client": 2, "xp_model_nam": 2, "lastli": 2, "run_evalu": 2, "upload": 2, "And": 2, "upload_result": 2, "experiment_prefix": 2, "num_repetit": 2, "view": 2, "386a3620": 2, "smith": 2, "9e1cc3cb": 2, "9d6a": 2, "4356": 2, "ab34": 2, "138e0abe8be4": 2, "8741976e": 2, "5268": 2, "4b75": 2, "949f": 2, "99477dde5d64": 2, "selectedsess": 2, "b831dc1e": 2, "90bc": 2, "4ed8": 2, "8080": 2, "fb42444724d6": 2, "4it": 2, "latest": [2, 3, 4], "modul": [2, 4], "tobia": 2, "evaluate_modul": 2, "6fc70b7be0088120a372dfdd5d320b39b8bb3630cb8029b193941d9376e86bb0": 2, "tue": 2, "nov": 2, "couldn": 2, "5it": 2, "5053784e": 2, "64445871": 2, "a53c": 2, "44b1": 2, "a422": 2, "4f49b2f9656f": 2, "69": 2, "4b29f3c9": 2, "9ef7e39a": 2, "2add": 2, "410c": 2, "89f8": 2, "9f1a8b198cf1": 2, "61": 2, "df": 2, "to_panda": 2, "insert": 2, "combined_df": 2, "concat": 2, "ignore_index": 2, "execution_tim": 2, "example_id": 2, "333333": 2, "224388": 2, "feb10f92": 2, "3167": 2, "41f3": 2, "bb1c": 2, "d271153a31a8": 2, "5b196b22": 2, "9f4c": 2, "489c": 2, "b020": 2, "7823208b42d6": 2, "348101": 2, "722464": 2, "c310f159": 2, "064a": 2, "4035": 2, "97c3": 2, "a25bbf43abc2": 2, "386076": 2, "704104": 2, "f7f24899": 2, "dd50": 2, "409e": 2, "93cc": 2, "6fb1622b60bf": 2, "443038": 2, "725059": 2, "242856d6": 2, "efb5": 2, "4101": 2, "b1cf": 2, "5805532838ac": 2, "373418": 2, "795302": 2, "ce975169": 2, "a0ab": 2, "40ce": 2, "8e32": 2, "efa28d06079d": 2, "stat": 2, "groupbi": 2, "agg": 2, "std": 2, "round": 2, "sort": 2, "sort_valu": 2, "figur": [2, 4], "subplot": 2, "side": 2, "pyplot": 2, "plt": 2, "numpi": 2, "np": 2, "ax1": 2, "ax2": 2, "figsiz": 2, "2ecc71": 2, "3498db": 2, "e74c3c": 2, "bleu_mean": 2, "bleu_std": 2, "enumer": [2, 3], "errorbar": 2, "yerr": 2, "fmt": 2, "markers": 2, "capsiz": 2, "label": [2, 4], "alpha": [2, 4], "set_ylabel": 2, "set_titl": 2, "set_xtick": 2, "set_xticklabel": 2, "rotat": 2, "set_ylim": 2, "bottom": 2, "axi": 2, "legend": 2, "exec_mean": 2, "exec_std": 2, "tight_layout": 2, "ndetail": 2, "4038": 2, "0453": 2, "7815": 2, "0433": 2, "3768": 2, "0424": 2, "8343": 2, "2208": 2, "3519": 2, "0775": 2, "9122": 2, "1482": 2, "377": 2, "042": 2, "83": 2, "078": 2, "slower": 2, "fastest": 2, "04": [2, 3], "latenc": [2, 3], "speed": 2, "interestingli": 2, "longer": 2, "decoupl": 2, "friendli": [2, 3], "reload": 2, "facilit": 2, "pleas": 2, "promptfooconfig": 2, "model_comparison": 2, "config": 2, "safe_load": 2, "pretti": 2, "dump": 2, "default_flow_styl": 2, "sort_kei": 2, "prompt1": 2, "defaulttest": 2, "1000": 2, "ye": [2, 4], "csv": 2, "1000m": 2, "sure": [2, 3, 4], "millisecond": 2, "eval_data": 2, "latency_m": 2, "totallatencym": 2, "token_usag": 2, "tokenusag": 2, "assert_pass": 2, "assertpasscount": 2, "assert_fail": 2, "assertfailcount": 2, "prompt_token": 2, "num_request": 2, "numrequest": 2, "ipython": 2, "markdown": [2, 3], "2463": 2, "000035": 2, "3773": 2, "004620": 2, "1669": 2, "000091": 2, "1669m": 2, "highest": 2, "3773m": 2, "00462": 2, "promptfool": 2, "manual": 2, "redefin": 2, "prompt_comparison": 2, "prompt2": 2, "prompt3": 2, "Not": 2, "prompt_fil": 2, "prompt_cont": 2, "strip": 2, "join": [2, 3], "BE": 2, "again": 2, "prompt_id": 2, "promptid": 2, "gradingresult": 2, "split": [2, 3], "df_raw": 2, "column": 2, "reset_index": 2, "eas": 2, "seamless": 2, "hf": 2, "quick": 2, "plain": 2, "vanilla": 2, "ui": [2, 4], "defi": 2, "accustom": 2, "legaci": 2, "unsustain": 2, "prove": 2, "prd": 2, "cultiv": 2, "organiz": 2, "stagnat": 2, "alb": 2, "loubna": 2, "ben": 2, "anton": 2, "lozhkov": 2, "eli": 2, "bakouch": 2, "gabriel": 2, "mart\u00edn": 2, "bl\u00e1zquez": 2, "lewi": 2, "tunstal": 2, "agust\u00edn": 2, "piquer": 2, "andr": 2, "marafioti": 2, "cyril": 2, "zakka": 2, "leandro": 2, "von": 2, "werra": 2, "thoma": 2, "wolf": 2, "are24": 2, "judgearena": 2, "bps99": 2, "salli": 2, "pott": 2, "barbara": 2, "557": 2, "sciencedirect": 2, "s0377221798003646": 2, "doi": [2, 4], "org": [2, 4], "1016": 2, "s0377": 2, "2217": 2, "00364": 2, "ctj": 2, "jerri": 2, "tworek": 2, "heewoo": 2, "jun": 2, "qime": 2, "yuan": 2, "henriqu": 2, "pond": 2, "de": 2, "oliveira": 2, "pinto": 2, "jare": 2, "kaplan": 2, "harri": 2, "edward": 2, "yuri": 2, "burda": 2, "nichola": 2, "joseph": 2, "greg": 2, "brockman": 2, "rai": 2, "raul": 2, "puri": 2, "gretchen": 2, "krueger": 2, "michael": [2, 4], "petrov": 2, "heidi": 2, "khlaaf": 2, "girish": 2, "sastri": 2, "pamela": 2, "mishkin": 2, "brook": 2, "chan": 2, "scott": 2, "grai": 2, "nick": 2, "ryder": 2, "mikhail": 2, "pavlov": 2, "alethea": 2, "lukasz": 2, "kaiser": 2, "mohammad": 2, "bavarian": 2, "clemen": 2, "winter": 2, "philipp": 2, "tillet": 2, "felip": 2, "petroski": 2, "dave": 2, "cum": 2, "matthia": 2, "plappert": 2, "fotio": 2, "chantzi": 2, "elizabeth": 2, "barn": 2, "ariel": 2, "herbert": 2, "voss": 2, "hebgen": 2, "guss": 2, "nichol": 2, "paino": 2, "nikola": 2, "tezak": 2, "jie": 2, "tang": 2, "igor": 2, "babuschkin": 2, "suchir": 2, "balaji": 2, "shantanu": 2, "jain": 2, "saunder": 2, "christoph": 2, "hess": 2, "andrew": 2, "carr": 2, "jan": 2, "leik": 2, "josh": 2, "achiam": 2, "vedant": 2, "misra": 2, "evan": 2, "morikawa": 2, "alec": 2, "radford": 2, "matthew": 2, "knight": 2, "mile": 2, "brundag": 2, "mira": 2, "murati": 2, "kati": 2, "mayer": 2, "peter": 2, "welind": 2, "bob": [2, 4], "mcgrew": 2, "dario": 2, "amodei": 2, "sam": 2, "mccandlish": 2, "ilya": 2, "sutskev": 2, "wojciech": 2, "zaremba": 2, "arxiv": [2, 4], "ab": [2, 4], "2107": 2, "03374": 2, "cz": 2, "lianmin": 2, "ying": 2, "sheng": 2, "anastasio": 2, "angelopoulo": 2, "tianl": 2, "dacheng": 2, "hao": 2, "zhang": 2, "banghua": 2, "zhu": 2, "jordan": 2, "gonzalez": 2, "ion": 2, "stoica": 2, "2403": 2, "04132": 2, "cho24a": 2, "francoi": 2, "arcpriz": 2, "cho24b": 2, "dglh24": 2, "yann": 2, "bal\u00e1z": 2, "galambosi": 2, "perci": 2, "tatsunori": 2, "hashimoto": 2, "debia": 2, "2404": 2, "04475": 2, "fac24a": 2, "wiki": [2, 4], "fac24b": 2, "fac24c": 2, "doc": [2, 3, 4], "model_doc": 2, "gpt2": 2, "fac24d": 2, "cookbook": 2, "en": [2, 4], "llm_judg": 2, "fac24": 2, "fac24f": 2, "blog": [2, 4], "fhwt23": 2, "cl\u00e9mentin": 2, "nathan": 2, "habib": 2, "hbb": 2, "dan": 2, "collin": 2, "burn": 2, "steven": 2, "basart": 2, "andi": 2, "zou": 2, "manta": 2, "mazeika": 2, "dawn": 2, "song": 2, "jacob": 2, "steinhardt": 2, "03300": 2, "hbd": 2, "ari": 2, "du": 2, "maxwel": 2, "forb": 2, "yejin": 2, "choi": 2, "curiou": 2, "neural": [2, 4], "degener": 2, "1904": 2, "09751": 2, "hyc": 2, "binyuan": 2, "jian": 2, "zeyu": 2, "cui": 2, "jiaxi": 2, "dayiheng": 2, "liu": [2, 4], "lei": 2, "tianyu": 2, "jiajun": 2, "bowen": 2, "yu": 2, "kai": 2, "dang": 2, "coder": 2, "preprint": [2, 4], "2409": 2, "12186": 2, "lx": 2, "zhen": 2, "xiaohan": 2, "xu": 2, "tao": 2, "shen": 2, "jia": 2, "gu": 2, "yuxuan": 2, "lai": 2, "chongyang": 2, "shuai": 2, "ma": 2, "nlg": 2, "2401": 2, "07103": 2, "lbl": 2, "rishi": 2, "bommasani": 2, "toni": 2, "lee": [2, 4], "dimitri": 2, "tsipra": 2, "dilara": 2, "soylu": 2, "michihiro": 2, "yasunaga": 2, "yian": 2, "deepak": 2, "narayanan": 2, "yuhuai": 2, "wu": [2, 4], "ananya": 2, "kumar": 2, "benjamin": 2, "newman": 2, "binhang": 2, "bobbi": 2, "yan": 2, "ce": 2, "christian": 2, "cosgrov": 2, "r\u00e9": 2, "diana": 2, "acosta": 2, "nava": 2, "drew": 2, "hudson": 2, "eric": 2, "zelikman": 2, "esin": 2, "durmu": 2, "faisal": 2, "ladhak": 2, "frieda": 2, "rong": 2, "hongyu": 2, "ren": 2, "huaxiu": 2, "yao": 2, "jue": 2, "keshav": 2, "santhanam": 2, "laurel": 2, "orr": 2, "lucia": 2, "mert": 2, "yuksekgonul": 2, "mirac": 2, "suzgun": 2, "kim": 2, "neel": 2, "guha": 2, "niladri": 2, "chatterji": 2, "omar": 2, "khattab": 2, "henderson": 2, "qian": 2, "huang": 2, "ryan": 2, "chi": [2, 4], "sang": 2, "xie": 2, "shibani": 2, "santurkar": 2, "surya": 2, "ganguli": 2, "icard": 2, "tianyi": 2, "vishrav": 2, "chaudhari": 2, "xuechen": 2, "yifan": 2, "yuhui": 2, "yuta": 2, "koreeda": 2, "2211": 2, "09110": 2, "lbc24": 2, "yuchen": 2, "ronan": 2, "le": 2, "bra": 2, "allenai": 2, "lhe22": 2, "stephani": 2, "hilton": 2, "owain": 2, "mimic": 2, "falsehood": 2, "2109": 2, "07958": 2, "pro24": 2, "dev": 2, "ras24": 2, "sebastian": 2, "scratch": 2, "isbn": 2, "1633437166": 2, "srr": 2, "aarohi": 2, "abhinav": 2, "rastogi": 2, "abhishek": 2, "rao": 2, "abu": 2, "awal": 2, "md": [2, 4], "shoeb": 2, "abubakar": 2, "abid": 2, "adam": 2, "fisch": 2, "brown": 2, "santoro": 2, "aditya": 2, "gupta": 2, "adri\u00e0": 2, "garriga": 2, "alonso": 2, "agnieszka": 2, "kluska": 2, "aitor": 2, "lewkowycz": 2, "akshat": 2, "agarw": 2, "warstadt": 2, "alexand": [2, 4], "kocurek": 2, "ali": 2, "safaya": 2, "tazarv": 2, "alic": [2, 4], "xiang": 2, "alicia": 2, "parrish": 2, "allen": 2, "nie": 2, "aman": 2, "hussain": 2, "amanda": 2, "askel": 2, "dsouza": 2, "ambros": 2, "slone": 2, "ameet": 2, "rahan": 2, "anantharaman": 2, "iyer": 2, "ander": 2, "andreassen": 2, "madotto": 2, "santilli": 2, "stuhlm\u00fcller": 2, "la": 2, "lampinen": 2, "angela": 2, "jiang": 2, "angelica": 2, "anh": 2, "vuong": 2, "animesh": 2, "anna": 2, "gottardi": 2, "antonio": 2, "norelli": 2, "anu": 2, "venkatesh": 2, "arash": 2, "gholamidavoodi": 2, "arfa": 2, "tabassum": 2, "arul": 2, "menez": 2, "arun": 2, "kirubarajan": 2, "asher": 2, "mullokandov": 2, "ashish": 2, "sabharw": 2, "herrick": 2, "avia": 2, "efrat": 2, "aykut": 2, "erdem": 2, "ayla": 2, "karaka\u015f": 2, "robert": 2, "bao": 2, "loe": 2, "barret": 2, "zoph": 2, "bart\u0142omiej": 2, "bojanowski": 2, "batuhan": 2, "\u00f6zyurt": 2, "behnam": 2, "hedayatnia": 2, "neyshabur": 2, "inden": 2, "benno": 2, "stein": 2, "berk": 2, "ekmekci": 2, "blake": 2, "howald": 2, "bryan": 2, "orinion": 2, "cameron": [2, 4], "diao": 2, "dour": 2, "catherin": 2, "stinson": 2, "cedrick": 2, "argueta": 2, "c\u00e9sar": 2, "ferri": 2, "ram\u00edrez": 2, "chandan": 2, "singh": 2, "charl": 2, "rathkopf": 2, "chenlin": 2, "meng": 2, "chitta": 2, "baral": 2, "chiyu": 2, "callison": 2, "burch": 2, "wait": 2, "voigt": 2, "cindi": 2, "ramirez": 2, "clara": 2, "rivera": 2, "clemencia": 2, "siro": 2, "colin": 2, "raffel": 2, "courtnei": 2, "ashcraft": 2, "cristina": 2, "garbacea": 2, "damien": 2, "sileo": 2, "garrett": 2, "kilman": 2, "roth": 2, "daniel": 2, "freeman": 2, "khashabi": 2, "levi": 2, "mosegu\u00ed": 2, "gonz\u00e1lez": 2, "perszyk": 2, "danni": 2, "hernandez": 2, "danqi": 2, "daphn": 2, "ippolito": 2, "dar": 2, "gilboa": 2, "david": 2, "dohan": 2, "drakard": 2, "jurgen": 2, "debajyoti": 2, "datta": 2, "deni": 2, "emelin": 2, "kleyko": 2, "deniz": 2, "yuret": 2, "derek": 2, "tam": [2, 4], "dieuwk": 2, "hupk": 2, "diganta": 2, "dilyar": 2, "buzan": 2, "coelho": 2, "mollo": 2, "diyi": 2, "dong": 2, "ho": 2, "dylan": 2, "schrader": 2, "ekaterina": 2, "shutova": 2, "ekin": 2, "dogu": 2, "cubuk": 2, "elad": 2, "segal": 2, "eleanor": 2, "hagerman": 2, "donowai": 2, "elli": 2, "pavlick": 2, "emanuel": 2, "rodola": 2, "emma": 2, "lam": 2, "chu": 2, "erkut": 2, "erni": 2, "ethan": 2, "dyer": 2, "jerzak": 2, "eunic": 2, "engefu": 2, "manyasi": 2, "evgenii": 2, "zheltonozhskii": 2, "fanyu": 2, "xia": 2, "fatemeh": 2, "siar": 2, "fernando": 2, "mart\u00ednez": 2, "plume": 2, "francesca": 2, "happ\u00e9": 2, "gaurav": 2, "mishra": 2, "genta": 2, "indra": 2, "winata": 2, "gerard": 2, "melo": 2, "germ\u00e1n": 2, "kruszewski": 2, "giambattista": 2, "parascandolo": 2, "giorgio": 2, "mariani": 2, "gloria": 2, "gonzalo": 2, "jaimovitch": 2, "l\u00f3pez": 2, "gregor": 2, "betz": 2, "gui": 2, "gur": 2, "hana": 2, "galijasev": 2, "hannah": 2, "rashkin": 2, "hannaneh": 2, "hajishirzi": 2, "harsh": 2, "mehta": 2, "hayden": 2, "bogar": 2, "henri": 2, "shevlin": 2, "hinrich": 2, "sch\u00fctze": 2, "hiromu": 2, "yakura": 2, "hongm": 2, "hugh": 2, "mee": 2, "wong": 2, "ian": 2, "ng": 2, "isaac": 2, "nobl": 2, "jaap": 2, "jumelet": 2, "jack": 2, "geissing": 2, "jackson": 2, "kernion": 2, "jaehoon": 2, "jaim": 2, "fern\u00e1ndez": 2, "fisac": 2, "jame": 2, "simon": 2, "koppel": 2, "koco\u0144": 2, "jana": 2, "thompson": 2, "janel": 2, "wingfield": 2, "jarema": 2, "radom": 2, "jascha": 2, "sohl": 2, "dickstein": 2, "jason": 2, "phang": 2, "yosinski": 2, "jekaterina": 2, "novikova": 2, "jell": 2, "bosscher": 2, "jennif": 2, "marsh": 2, "jeremi": 2, "jeroen": 2, "taal": 2, "jess": 2, "engel": 2, "jesujoba": 2, "alabi": 2, "jiacheng": 2, "jiam": 2, "jillian": 2, "joan": 2, "waweru": 2, "john": 2, "burden": 2, "miller": 2, "bali": 2, "jonathan": 2, "batcheld": 2, "berant": 2, "j\u00f6rg": 2, "frohberg": 2, "jo": 2, "rozen": 2, "orallo": 2, "boudeman": 2, "guerr": 2, "joshua": 2, "tenenbaum": 2, "joyc": 2, "chua": 2, "kamil": 2, "kanclerz": 2, "karen": 2, "livescu": 2, "karl": 2, "krauth": 2, "karthik": 2, "gopalakrishnan": 2, "katerina": 2, "ignatyeva": 2, "katja": 2, "markert": 2, "kaustubh": 2, "dhole": 2, "kevin": 2, "gimpel": 2, "omondi": 2, "kori": 2, "mathewson": 2, "kristen": 2, "chiafullo": 2, "ksenia": 2, "shkaruta": 2, "shridhar": 2, "kyle": 2, "mcdonel": 2, "richardson": 2, "laria": 2, "reynold": 2, "leo": 2, "gao": 2, "liam": 2, "dugan": 2, "lianhui": 2, "qin": 2, "lidia": 2, "contrera": 2, "ochando": 2, "loui": 2, "morenc": 2, "moschella": 2, "luci": 2, "ludwig": 2, "schmidt": 2, "luheng": 2, "lui": 2, "olivero": 2, "col\u00f3n": 2, "luke": 2, "metz": 2, "l\u00fctfi": 2, "kerem": 2, "\u015fenel": 2, "maarten": 2, "bosma": 2, "sap": 2, "maartj": 2, "hoev": 2, "maheen": 2, "farooqi": 2, "manaal": 2, "faruqui": 2, "marco": 2, "baturan": 2, "marelli": 2, "maru": 2, "maria": 2, "quintana": 2, "mari": 2, "tolkiehn": 2, "mario": 2, "giulianelli": 2, "martha": 2, "martin": 2, "potthast": 2, "leavitt": 2, "hagen": 2, "m\u00e1ty\u00e1": 2, "schubert": 2, "medina": 2, "orduna": 2, "baitemirova": 2, "melodi": 2, "arnaud": 2, "melvin": 2, "mcelrath": 2, "yee": 2, "cohen": 2, "ivanitskii": 2, "starritt": 2, "strube": 2, "micha\u0142": 2, "sw\u0119drowski": 2, "michel": 2, "bevilacqua": 2, "mihir": 2, "kale": 2, "cain": 2, "mime": 2, "mitch": 2, "walker": 2, "mo": 2, "tiwari": 2, "mohit": 2, "bansal": 2, "moin": 2, "aminnaseri": 2, "mor": 2, "geva": 2, "mozhdeh": 2, "gheini": 2, "mukund": 2, "varma": 2, "nanyun": 2, "peng": 2, "nayeon": 2, "neta": 2, "krakov": 2, "doiron": 2, "nicol": 2, "martinez": 2, "nikita": 2, "nangia": 2, "nikla": 2, "decker": 2, "muennighoff": 2, "nitish": 2, "shirish": 2, "keskar": 2, "niveditha": 2, "noah": 2, "constant": 2, "fiedel": 2, "nuan": 2, "wen": 2, "oliv": 2, "agha": 2, "elbaghdadi": 2, "omer": 2, "moreno": 2, "casar": 2, "parth": 2, "doshi": 2, "pascal": 2, "fung": 2, "paul": 2, "pu": 2, "vicol": 2, "pegah": 2, "alipoormolabashi": 2, "peiyuan": 2, "liao": 2, "eckerslei": 2, "phu": 2, "mon": 2, "htut": 2, "pinyu": 2, "hwang": 2, "piotr": 2, "mi\u0142kowski": 2, "piyush": 2, "patil": 2, "pouya": 2, "pezeshkpour": 2, "priti": 2, "oli": 2, "qiaozhu": 2, "mei": 2, "qing": 2, "lyu": 2, "qinlang": 2, "rabin": 2, "banjad": 2, "rachel": 2, "etta": 2, "rudolph": 2, "raefer": 2, "rahel": 2, "haback": 2, "ramon": 2, "risco": 2, "rapha\u00ebl": 2, "milli\u00e8r": 2, "rhythm": 2, "garg": 2, "rif": 2, "saurou": 2, "riku": 2, "arakawa": 2, "robb": 2, "raymaek": 2, "frank": 2, "rohan": 2, "sikand": 2, "roman": 2, "novak": 2, "sitelew": 2, "lebra": 2, "rosann": 2, "rowan": 2, "rui": [2, 4], "ruslan": 2, "salakhutdinov": 2, "stoval": 2, "teehan": 2, "rylan": 2, "sahib": 2, "saif": 2, "sajant": 2, "anand": 2, "dillav": 2, "shleifer": 2, "wiseman": 2, "samuel": 2, "gruetter": 2, "bowman": 2, "schoenholz": 2, "sanghyun": 2, "han": 2, "sanjeev": 2, "kwatra": 2, "sarah": 2, "sarik": 2, "ghazarian": 2, "sayan": 2, "ghosh": 2, "sean": 2, "casei": 2, "bischoff": 2, "gehrmann": 2, "schuster": 2, "sepideh": 2, "sadeghi": 2, "shadi": 2, "hamdan": 2, "sharon": 2, "zhou": 2, "shashank": 2, "sherri": 2, "shi": 2, "shikhar": 2, "shima": 2, "asaadi": 2, "shixiang": 2, "shane": 2, "shubh": 2, "pachchigar": 2, "shubham": 2, "toshniw": 2, "shyam": 2, "upadhyai": 2, "shyamolima": 2, "debnath": 2, "siamak": 2, "shakeri": 2, "thormey": 2, "melzi": 2, "siva": 2, "reddi": 2, "sneha": 2, "priscilla": 2, "makini": 2, "soo": 2, "hwan": 2, "spencer": 2, "toren": 2, "sriharsha": 2, "hatwar": 2, "stanisla": 2, "dehaen": 2, "stefan": 2, "divic": 2, "stefano": 2, "ermon": 2, "stella": 2, "biderman": 2, "stephen": 2, "prasad": 2, "piantadosi": 2, "stuart": 2, "shieber": 2, "summer": 2, "misherghi": 2, "svetlana": 2, "kiritchenko": 2, "swaroop": 2, "tal": 2, "linzen": 2, "tariq": 2, "tatsu": 2, "te": 2, "th\u00e9o": 2, "desbord": 2, "theodor": 2, "rothschild": 2, "phan": 2, "tiberiu": 2, "nkinyili": 2, "timo": 2, "schick": 2, "timofei": 2, "kornev": 2, "titu": 2, "tunduni": 2, "gerstenberg": 2, "trenton": 2, "trishala": 2, "neeraj": 2, "tushar": 2, "khot": 2, "tyler": 2, "shultz": 2, "uri": 2, "shaham": 2, "vera": 2, "demberg": 2, "victoria": 2, "nyamai": 2, "vika": 2, "raunak": 2, "vinai": 2, "ramasesh": 2, "udai": 2, "prabhu": 2, "vishakh": 2, "padmakumar": 2, "vivek": 2, "srikumar": 2, "fedu": 2, "wout": 2, "vossen": 2, "xiaoyu": 2, "tong": 2, "xinran": 2, "zhao": 2, "xinyi": 2, "xudong": 2, "yadollah": 2, "yaghoobzadeh": 2, "yair": 2, "lakretz": 2, "yangqiu": 2, "yasaman": 2, "bahri": 2, "yichi": 2, "yide": 2, "yifu": 2, "yonatan": 2, "belinkov": 2, "hou": 2, "yufang": 2, "yuntao": 2, "bai": 2, "zachari": 2, "seid": 2, "zhuoy": 2, "zijian": 2, "ziji": 2, "j": [2, 4], "zirui": 2, "ziyi": 2, "extrapol": 2, "2206": 2, "04615": 2, "wpn": 2, "yada": 2, "pruksachatkun": 2, "amanpreet": 2, "julian": 2, "felix": 2, "hill": 2, "stickier": 2, "wsm": 2, "1804": 2, "07461": 2, "wtb": 2, "yi": [2, 4], "tai": 2, "borgeaud": 2, "dani": 2, "yogatama": 2, "denni": 2, "donald": 2, "metzler": 2, "ed": 2, "h": 2, "oriol": 2, "vinyal": 2, "dean": 2, "07682": 2, "wdr": 2, "doolei": 2, "manlei": 2, "arka": 2, "pal": 2, "feuer": 2, "siddhartha": 2, "ravid": 2, "shwartz": 2, "ziv": 2, "khalid": 2, "saifullah": 2, "siddartha": 2, "naidu": 2, "chinmai": 2, "hegd": 2, "lecun": 2, "tom": 2, "goldstein": 2, "willi": 2, "neiswang": 2, "micah": 2, "goldblum": 2, "2406": 2, "19314": 2, "yyh": 2, "baosong": 2, "bo": 2, "chengpeng": 2, "chengyuan": 2, "fei": 2, "guant": 2, "haoran": 2, "huan": 2, "jialong": 2, "jialin": 2, "jianhong": 2, "tu": 2, "jianwei": 2, "jianxin": 2, "jin": 2, "jingren": 2, "jinz": 2, "jinzheng": 2, "junyang": 2, "keme": 2, "lu": 2, "keqin": 2, "kexin": 2, "mingfeng": 2, "xue": 2, "ni": 2, "pei": 2, "ru": 2, "men": 2, "ruiz": 2, "runji": 2, "shiji": 2, "sinan": 2, "tan": 2, "tianhang": 2, "tianhao": 2, "wenbin": 2, "ge": 2, "xiaodong": 2, "deng": 2, "xiaohuan": 2, "xingzhang": 2, "xinyu": 2, "xipin": 2, "xuancheng": 2, "fan": 2, "yichang": 2, "wan": 2, "yunfei": 2, "yuqiong": 2, "zhenru": 2, "zhihao": 2, "2407": 2, "10671": 2, "zc": 2, "siyuan": 2, "zhuang": 2, "zhanghao": 2, "yonghao": 2, "zi": 2, "zhuohan": 2, "xing": 2, "2306": 2, "05685": 2, "huggingface24": 2, "06": [2, 4], "metaai24": 2, "far": 3, "possibli": 3, "eliot": 3, "english": 3, "thumb": 3, "\u00be": 3, "max_output_token": 3, "4096": 3, "16384": 3, "contrari": 3, "surpass": 3, "truncat": 3, "max_input_token": 3, "input_cost_per_token": 3, "output_cost_per_token": 3, "11b": 3, "v1": 3, "128000": 3, "5e": 3, "20241022": 3, "8192": 3, "200000": 3, "3e": 3, "0613": 3, "6e": 3, "1e": 3, "gemini": 3, "flash": 3, "1048576": 3, "2097152": 3, "05e": 3, "incomplet": 3, "abruptli": 3, "shallow": 3, "thorough": 3, "dissatisfact": 3, "frustrat": 3, "creation": 3, "feasibl": 3, "10k": 3, "diagram": 3, "charactertextsplitt": 3, "tiktoken": 3, "sequenti": 3, "newlin": 3, "broadli": [3, 4], "want": [3, 4], "cheap": 3, "speciali": 3, "naiv": 3, "nltk": 3, "spaci": 3, "recurs": 3, "divid": 3, "hierarch": 3, "talk": 3, "theme": 3, "splitter": 3, "html": [3, 4], "get_chunk": 3, "chunk_siz": 3, "chunk_overlap": 3, "langchain_text_splitt": 3, "text_splitt": 3, "from_tiktoken_encod": 3, "split_text": 3, "persona": 3, "task": [3, 4], "langchain_cor": [3, 4], "prompttempl": 3, "get_base_prompt_templ": 3, "base_prompt": [3, 4], "from_templ": 3, "llmchain": 3, "togeth": 3, "parser": [3, 4], "output_pars": 3, "stroutputpars": 3, "langchain_commun": 3, "chat_model": 3, "chatlitellm": 3, "get_llm_chain": 3, "prompt_templ": [3, 4], "llm_chain": [3, 4], "api_key_label": 3, "upper": 3, "_api_kei": 3, "get_dynamic_prompt_templ": 3, "get_dynamic_prompt_param": 3, "prompt_param": 3, "part_idx": 3, "total_part": 3, "chat_context": 3, "param": 3, "dynamic_prompt_param": 3, "introduct": 3, "elif": 3, "merg": 3, "concaten": 3, "generate_report": 3, "input_cont": 3, "llm_model_nam": 3, "report_part": 3, "num_part": 3, "dinam": 3, "priovid": 3, "invok": [3, 4], "cummul": 3, "max_chunk_s": 3, "max_chunk_overlap": 3, "readabl": 3, "apple_report": 3, "luation": 3, "disciplin": 3, "smooth": 3, "subhead": 3, "despit": [3, 4], "depth": 3, "overlook": 3, "preserv": 3, "easier": [3, 4], "preprocess": [3, 4], "necessit": 3, "meticul": 3, "bottleneck": 3, "mustafa": 3, "suleyman": 3, "infinit": 3, "fewer": 3, "progress": 3, "condens": 3, "versatil": 3, "drive": [3, 4], "grace": 3, "fallback": 3, "empow": 3, "crucial": [3, 4], "langchain24": 3, "how_to": 3, "freedom": 4, "julia": 4, "easili": 4, "notebook": 4, "overrid": 4, "response_cont": 4, "wow": 4, "lot": 4, "breakdown": 4, "impress": 4, "huge": 4, "serious": 4, "is_json": 4, "myjson": 4, "valueerror": 4, "trial": 4, "elicit": 4, "wrangl": 4, "hoc": 4, "streamlin": 4, "subsequ": 4, "dataset": 4, "unwant": 4, "overflow": 4, "overwhelm": 4, "twitter": 4, "youtub": 4, "publish": 4, "schema": 4, "blueprint": 4, "nativ": 4, "json_format": 4, "person1": 4, "q1": 4, "person2": 4, "nest": 4, "todai": 4, "thellm": 4, "unend": 4, "whitespac": 4, "forget": 4, "throw": 4, "somewher": 4, "json_object": 4, "sheer": 4, "circul": 4, "vertex": 4, "worri": 4, "enum": 4, "refus": 4, "simpler": 4, "strongli": 4, "secextract": 4, "mentioned_ent": 4, "mentioned_plac": 4, "extract_from_sec_fil": 4, "sec_filing_text": 4, "hint": 4, "prompt_extract": 4, "sec_extract": 4, "washington": 4, "usabl": 4, "beg": 4, "with_structured_output": 4, "runnabl": 4, "typeddict": 4, "qu": 4, "langchain_openai": 4, "chatopenai": 4, "chatprompttempl": 4, "extract_from_sec_filing_langchain": 4, "structured_llm": 4, "from_messag": 4, "sec_extraction_langchain": 4, "hood": 4, "logit": 4, "willard": 4, "louf": 4, "reformul": 4, "finit": 4, "fsm": 4, "s_": 4, "sim": 4, "s_t": 4, "theta": 4, "s_1": 4, "v": 4, "mathbb": 4, "mask": 4, "tild": 4, "odot": 4, "rightarrow": 4, "boolean": 4, "wise": 4, "formul": 4, "regex": 4, "tran": 4, "thien": 4, "automaton": 4, "dfa": 4, "decod": 4, "outgo": 4, "renorm": 4, "yy": 4, "nn": 4, "ever": 4, "aa": 4, "lwai": 4, "prop": 4, "yynnaa": 4, "qwen": 4, "malform": 4, "sec_extraction_outlin": 4, "zsp": 4, "zicorp": 4, "phenomenon": 4, "popular": 4, "cpp": 4, "gbnf": 4, "ggml": 4, "bnf": 4, "ggerganov": 4, "accomplish": 4, "backu": 4, "naur": 4, "wikipedia": 4, "contributor": 4, "strictli": 4, "soon": 4, "curl": 4, "fssl": 4, "sh": 4, "extract_entities_from_sec_fil": 4, "suffix": 4, "ollama_structured_output_prompt_suffix": 4, "ollama_structured_output_temperatur": 4, "mistral": 4, "llama2": 4, "uncensor": 4, "model_json_schema": 4, "response_json": 4, "wrapper": 4, "exllama2": 4, "mlx": 4, "lm": 4, "medium": 4, "know": 4, "chanc": 4, "correctli": 4, "famili": 4, "furthermor": 4, "nonetheless": 4, "studi": 4, "wrap": 4, "gemma": 4, "uncov": 4, "wors": 4, "extran": 4, "dispar": 4, "preval": 4, "rapidli": 4, "fashion": 4, "remark": 4, "me": 4, "speak": 4, "freeli": 4, "aider": 4, "outweigh": 4, "rebutt": 4, "argu": 4, "reproduct": 4, "paint": 4, "pictur": 4, "verif": 4, "dottxt": 4, "flaw": 4, "uneven": 4, "didn": 4, "conflat": 4, "argument": 4, "drawback": 4, "unlock": 4, "wider": 4, "thank": 4, "pfiffer": 4, "aid24": 4, "dot24": 4, "sai": 4, "demo": 4, "tree": 4, "gge24": 4, "blob": 4, "readm": 4, "llf": 4, "xieyang": 4, "frederick": 4, "fiannaca": 4, "terri": 4, "koo": 4, "dixon": 4, "cai": 4, "ea": 4, "ny": 4, "usa": 4, "machineri": 4, "1145": 4, "3613905": 4, "3650756": 4, "ln": 4, "xuan": 4, "hai": 4, "nguyen": 4, "ngoc": 4, "tiviati": 4, "hieu": 4, "dao": 4, "shafiq": 4, "joti": 4, "kenji": 4, "kawaguchi": 4, "nanci": 4, "min": 4, "kan": 4, "2408": 4, "08656": 4, "out24": 4, "twt": 4, "zhi": 4, "cheng": 4, "kuang": 4, "tsai": 4, "chieh": 4, "hung": 4, "yun": 4, "nung": 4, "02442": 4, "tt24": 4, "vivien": 4, "vivien000": 4, "wl23": 4, "brandon": 4, "r\u00e9mi": 4, "2307": 4, "09702": 4, "wikipediacontributors24": 4, "wiktionari": 4, "naur_form": 4}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"introduct": [0, 1, 2, 4], "content": [0, 2, 3, 4], "core": 0, "challeng": 0, "we": 0, "ll": 0, "address": 0, "A": [0, 1], "practic": [0, 1, 4], "approach": 0, "note": 0, "perspect": 0, "who": 0, "thi": 0, "book": 0, "i": 0, "For": 0, "outcom": 0, "prerequisit": 0, "set": 0, "up": 0, "your": 0, "environ": 0, "python": 0, "setup": 0, "api": [0, 4], "kei": [0, 2, 3], "configur": 0, "code": 0, "repositori": 0, "troubleshoot": 0, "common": 0, "issu": 0, "about": 0, "author": 0, "": 0, "tame": 1, "llm": [1, 2], "guid": 1, "pitfal": 1, "open": 1, "sourc": 1, "softwar": [1, 2], "chapter": 1, "1": [1, 3], "2": [1, 3], "wrestl": [1, 4], "structur": [1, 4], "output": [1, 3, 4], "3": [1, 3], "input": 1, "size": [1, 3], "length": [1, 3], "limit": [1, 3], "4": [1, 3], "5": 1, "The": [1, 2], "eval": [1, 2], "gap": [1, 2], "6": 1, "hallucin": 1, "realiti": 1, "7": 1, "safeti": 1, "concern": 1, "8": 1, "cost": [1, 3], "factor": 1, "9": 1, "break": 1, "free": 1, "from": 1, "cloud": 1, "provid": [1, 4], "appendix": 1, "tool": [1, 2, 4], "resourc": 1, "citat": 1, "non": 2, "determinist": 2, "gener": [2, 3], "machin": 2, "emerg": 2, "properti": 2, "problem": [2, 3, 4], "statement": [2, 3, 4], "tradit": 2, "v": 2, "design": 2, "applic": 2, "test": 2, "requir": 2, "matrix": 2, "conceptu": 2, "overview": 2, "consider": [2, 3], "metric": 2, "evalu": 2, "task": 2, "model": [2, 3], "base": [2, 3], "human": 2, "benchmark": 2, "leaderboard": 2, "lightev": 2, "mmlu": 2, "econometr": 2, "dataset": 2, "sampl": 2, "famili": 2, "us": 2, "langsmith": 2, "promptfoo": 2, "comparison": [2, 3, 4], "conclus": [2, 3, 4], "refer": [2, 3, 4], "what": 3, "ar": 3, "token": 3, "across": 3, "chunk": 3, "contextu": 3, "link": 3, "long": 3, "form": 3, "step": 3, "write": 3, "prompt": [3, 4], "templat": 3, "construct": 3, "dynam": 3, "paramet": 3, "report": 3, "exampl": 3, "usag": 3, "discuss": [3, 4], "implic": 3, "futur": 3, "user": 4, "need": 4, "solut": 4, "strategi": 4, "techniqu": 4, "One": 4, "shot": 4, "specif": 4, "json": 4, "mode": 4, "langchain": 4, "outlin": 4, "ollama": 4, "compar": 4, "framework": 4, "best": 4, "research": 4, "ongo": 4, "debat": 4, "acknowledg": 4}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinxcontrib.bibtex": 9, "sphinx": 57}, "alltitles": {"Introduction": [[0, "introduction"], [2, "introduction"], [4, "introduction"]], "Contents": [[0, "contents"], [2, "contents"], [3, "contents"], [4, "contents"]], "Core Challenges We\u2019ll Address": [[0, "core-challenges-we-ll-address"]], "A Practical Approach": [[0, "a-practical-approach"]], "A Note on Perspective": [[0, "a-note-on-perspective"]], "Who This Book Is For": [[0, "who-this-book-is-for"]], "Outcomes": [[0, "outcomes"]], "Prerequisites": [[0, "prerequisites"]], "Setting Up Your Environment": [[0, "setting-up-your-environment"]], "Python Environment Setup": [[0, "python-environment-setup"]], "API Keys Configuration": [[0, "api-keys-configuration"]], "Code Repository": [[0, "code-repository"]], "Troubleshooting Common Issues": [[0, "troubleshooting-common-issues"]], "About the Author(s)": [[0, "about-the-author-s"]], "Taming LLMs": [[1, "taming-llms"]], "A Practical Guide to LLM Pitfalls with Open Source Software": [[1, "a-practical-guide-to-llm-pitfalls-with-open-source-software"]], "Chapter 1: Introduction": [[1, "chapter-1-introduction"]], "Chapter 2: Wrestling with Structured Output": [[1, "chapter-2-wrestling-with-structured-output"]], "Chapter 3: Input Size and Length Limitations": [[1, "chapter-3-input-size-and-length-limitations"]], "Chapter 4: Output Size and Length Limitations": [[1, "chapter-4-output-size-and-length-limitations"]], "Chapter 5: The Evals Gap": [[1, "chapter-5-the-evals-gap"]], "Chapter 6: Hallucination: The Reality Gap": [[1, "chapter-6-hallucination-the-reality-gap"]], "Chapter 7: Safety Concerns": [[1, "chapter-7-safety-concerns"]], "Chapter 8: The Cost Factor": [[1, "chapter-8-the-cost-factor"]], "Chapter 9: Breaking Free from Cloud Providers": [[1, "chapter-9-breaking-free-from-cloud-providers"]], "Appendix A: Tools and Resources": [[1, "appendix-a-tools-and-resources"]], "Citation": [[1, "citation"]], "The Evals Gap": [[2, "the-evals-gap"]], "Non-Deterministic Generative Machines": [[2, "non-deterministic-generative-machines"]], "Emerging Properties": [[2, "emerging-properties"]], "Problem Statement": [[2, "problem-statement"], [3, "problem-statement"], [4, "problem-statement"]], "Evals of Traditional Software vs LLMs": [[2, "evals-table"]], "Evals Design": [[2, "evals-design"]], "LLM Application Testing Requirements Matrix": [[2, "validation-requirements"]], "Conceptual Overview": [[2, "conceptual-overview"]], "Design Considerations": [[2, "design-considerations"]], "Metrics": [[2, "metrics"]], "Key Metrics for Evaluating Generative Tasks": [[2, "key-metrics"]], "Evaluators": [[2, "evaluators"]], "Model-Based Evaluation": [[2, "model-based-evaluation"]], "Human-Based Evaluation": [[2, "human-based-evaluation"]], "Evaluating Evaluators": [[2, "evaluating-evaluators"]], "Benchmarks and Leaderboards": [[2, "benchmarks-and-leaderboards"]], "Tools": [[2, "tools"]], "LightEval": [[2, "lighteval"]], "MMLU Econometrics Task Dataset sample": [[2, "mmlu-econometrics"]], "Model Families Evaluated Using LightEval": [[2, "model-families"]], "LangSmith": [[2, "langsmith"]], "PromptFoo": [[2, "promptfoo"]], "Comparison": [[2, "comparison"]], "Comparison of Lighteval, LangSmith, and Promptfoo": [[2, "tool-comparison"]], "Conclusion": [[2, "conclusion"], [3, "conclusion"], [4, "conclusion"]], "References": [[2, "references"], [3, "references"], [4, "references"]], "Output Size Limitations": [[3, "output-size-limitations"]], "What are Token Limits?": [[3, "what-are-token-limits"]], "Token Cost and Length Limitation Comparison Across Key Models": [[3, "token-cost-table"]], "Content Chunking with Contextual Linking": [[3, "content-chunking-with-contextual-linking"]], "Generating long-form content": [[3, "generating-long-form-content"]], "Step 1: Chunking the Content": [[3, "step-1-chunking-the-content"]], "Step 2: Writing the Base Prompt Template": [[3, "step-2-writing-the-base-prompt-template"]], "Step 3: Constructing Dynamic Prompt Parameters": [[3, "step-3-constructing-dynamic-prompt-parameters"]], "Step 4: Generating the Report": [[3, "step-4-generating-the-report"]], "Example Usage": [[3, "example-usage"]], "Discussion": [[3, "discussion"], [4, "discussion"]], "Implications": [[3, "implications"]], "Future Considerations": [[3, "future-considerations"]], "Wrestling with Structured Output": [[4, "wrestling-with-structured-output"]], "User Needs": [[4, "user-needs"]], "Solutions": [[4, "solutions"]], "Strategies": [[4, "strategies"]], "Techniques and Tools": [[4, "techniques-and-tools"]], "One-Shot Prompts": [[4, "one-shot-prompts"]], "Structured Output with Provider-Specific APIs": [[4, "structured-output-with-provider-specific-apis"]], "JSON Mode": [[4, "json-mode"]], "LangChain": [[4, "langchain"]], "Outlines": [[4, "outlines"]], "Ollama": [[4, "ollama"]], "Comparing Solutions": [[4, "comparing-solutions"]], "Structured Output Frameworks Comparison": [[4, "structured-output-frameworks"]], "Best Practices": [[4, "best-practices"]], "Research and Ongoing Debate": [[4, "research-and-ongoing-debate"]], "Acknowledgements": [[4, "acknowledgements"]]}, "indexentries": {}}) \ No newline at end of file diff --git a/tamingllms/_build/jupyter_execute/markdown/intro.ipynb b/tamingllms/_build/jupyter_execute/markdown/intro.ipynb index 02830f8..e797273 100644 --- a/tamingllms/_build/jupyter_execute/markdown/intro.ipynb +++ b/tamingllms/_build/jupyter_execute/markdown/intro.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "markdown", - "id": "3693a9ca", + "id": "c73deaa9", "metadata": {}, "source": [ "(intro)=\n", diff --git a/tamingllms/_build/jupyter_execute/notebooks/evals.ipynb b/tamingllms/_build/jupyter_execute/notebooks/evals.ipynb index 9419738..53833ae 100644 --- a/tamingllms/_build/jupyter_execute/notebooks/evals.ipynb +++ b/tamingllms/_build/jupyter_execute/notebooks/evals.ipynb @@ -14,6 +14,16 @@ "```\n", "```{contents}\n", "```\n", + "\n", + "## Introduction\n", + "\n", + "The advent of LLMs marks a pivotal shift in the landscape of software development and evaluation. Unlike traditional software systems, where deterministic outputs are the norm, LLMs introduce a realm of non-deterministic and generative behaviors that challenge conventional software engineering testing paradigms. This shift is not merely a technical evolution but a fundamental transformation in how we conceive, build, and assess software products.\n", + "\n", + "For those entrenched in traditional methodologies, the transition to LLM-driven systems may seem daunting. However, ignoring this change is not an option. The reliance on outdated testing frameworks that fail to account for the probabilistic nature of LLMs will inevitably lead to significant setbacks.\n", + "\n", + "To overcome these challenges, it is imperative to embrace the complexities of LLMs with a proactive mindset. This involves developing robust evaluation frameworks up-front, fostering a product development culture of continuous change, learning and adaptation.\n", + "\n", + "\n", "## Non-Deterministic Generative Machines\n", "\n", "One of the most fundamental challenges when building products with Large Language Models (LLMs) is their generative and non-deterministic nature. Unlike traditional software systems where the same input reliably produces the same output, LLMs can generate novel text that may not exist in their training data, and produce different responses each time they're queried - even with identical prompts and input data. This behavior is both a strength and a significant engineering challenge and product challenge.\n", @@ -26,21 +36,12 @@ "- Regulatory compliance becomes challenging to guarantee\n", "- User trust may be affected by inconsistent responses\n", "\n", - "### Temperature and Sampling\n", "\n", "The primary source of non-determinism in LLMs comes from their sampling strategies. During text generation, the model:\n", "1. Calculates probability distributions for each next token\n", "2. Samples from these distributions based on temperature settings\n", "3. Uses techniques like nucleus sampling {cite}`holtzman2020curiouscaseneuraltext` or top-k sampling to balance creativity and coherence\n", "\n", - "### The Temperature Spectrum\n", - "\n", - "- Temperature = 0: Most deterministic, but potentially repetitive\n", - "- Temperature = 1: Balanced creativity and coherence\n", - "- Temperature > 1: Increased randomness, potentially incoherent\n", - "\n", - "A temperature of 1 represents the unscaled probability scores for each token in the vocabulary. Decreasing the temperature closer to 0 sharpens the distribution, so the most likely token will have an even higher probability score. Conversely, increasing the temperature makes the distribution more uniform {cite}`build-llms-from-scratch-book`.\n", - "\n", "In this simple experiment, we use an LLM to write a single-statement executive summary of an input financial filing. We observe that even a simple parameter like temperature can dramatically alter model behavior in ways that are difficult to systematically assess. At temperature 0.0, responses are consistent but potentially too rigid. At 1.0, outputs become more varied but less predictable. At 2.0, responses can be wildly different and often incoherent. This non-deterministic behavior makes traditional software testing approaches inadequate." ] }, @@ -175,6 +176,11 @@ "cell_type": "markdown", "metadata": {}, "source": [ + "A temperature of 1 represents the unscaled probability scores for each token in the vocabulary. Decreasing the temperature closer to 0 sharpens the distribution, so the most likely token will have an even higher probability score. Conversely, increasing the temperature makes the distribution more uniform {cite}`build-llms-from-scratch-book`:\n", + "- Temperature = 0: Most deterministic, but potentially repetitive\n", + "- Temperature = 1: Balanced creativity and coherence\n", + "- Temperature > 1: Increased randomness, potentially incoherent\n", + "\n", "How can one effectively test an LLM-powered system when the same prompt can yield radically different outputs based on a single parameter? Traditional testing relies on predictable inputs and outputs, but LLMs force us to grapple with probabilistic behavior. While lower temperatures may seem safer for critical applications, they don't necessarily eliminate the underlying uncertainty. This highlights the need for new evaluation paradigms that can handle both deterministic and probabilistic aspects of LLM behavior." ] }, @@ -2530,6 +2536,19 @@ "```" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Conclusion\n", + "\n", + "Language models have fundamentally transformed how software is developed and evaluated. Unlike conventional systems that produce predictable outputs, LLMs generate varied, probabilistic responses that defy traditional testing approaches. While developers accustomed to deterministic systems may find this shift challenging, continuing to rely on legacy testing methods is unsustainable. These frameworks were not designed to handle the inherent variability of LLM outputs and will ultimately prove inadequate. \n", + "\n", + "Success requires embracing this new paradigm by implementing comprehensive evaluation strategies early - this is the new Product Requirements Document (PRD) - and cultivating an organizational mindset focused on iteration, experimentation and growth.\n", + "\n", + "The shift from traditional software testing to LLM evaluation is not just a change in tools but a transformation in mindset. Those who recognize and adapt to this shift will lead the way in harnessing the power of LLMs. However, the cost of inaction is not just technological stagnation, but potential business failure." + ] + }, { "cell_type": "markdown", "metadata": {}, diff --git a/tamingllms/notebooks/evals.ipynb b/tamingllms/notebooks/evals.ipynb index 3eeebfa..82dc3f6 100644 --- a/tamingllms/notebooks/evals.ipynb +++ b/tamingllms/notebooks/evals.ipynb @@ -14,6 +14,16 @@ "```\n", "```{contents}\n", "```\n", + "\n", + "## Introduction\n", + "\n", + "The advent of LLMs marks a pivotal shift in the landscape of software development and evaluation. Unlike traditional software systems, where deterministic outputs are the norm, LLMs introduce a realm of non-deterministic and generative behaviors that challenge conventional software engineering testing paradigms. This shift is not merely a technical evolution but a fundamental transformation in how we conceive, build, and assess software products.\n", + "\n", + "For those entrenched in traditional methodologies, the transition to LLM-driven systems may seem daunting. However, ignoring this change is not an option. The reliance on outdated testing frameworks that fail to account for the probabilistic nature of LLMs will inevitably lead to significant setbacks.\n", + "\n", + "To overcome these challenges, it is imperative to embrace the complexities of LLMs with a proactive mindset. This involves developing robust evaluation frameworks up-front, fostering a product development culture of continuous change, learning and adaptation.\n", + "\n", + "\n", "## Non-Deterministic Generative Machines\n", "\n", "One of the most fundamental challenges when building products with Large Language Models (LLMs) is their generative and non-deterministic nature. Unlike traditional software systems where the same input reliably produces the same output, LLMs can generate novel text that may not exist in their training data, and produce different responses each time they're queried - even with identical prompts and input data. This behavior is both a strength and a significant engineering challenge and product challenge.\n", @@ -26,21 +36,12 @@ "- Regulatory compliance becomes challenging to guarantee\n", "- User trust may be affected by inconsistent responses\n", "\n", - "### Temperature and Sampling\n", "\n", "The primary source of non-determinism in LLMs comes from their sampling strategies. During text generation, the model:\n", "1. Calculates probability distributions for each next token\n", "2. Samples from these distributions based on temperature settings\n", "3. Uses techniques like nucleus sampling {cite}`holtzman2020curiouscaseneuraltext` or top-k sampling to balance creativity and coherence\n", "\n", - "### The Temperature Spectrum\n", - "\n", - "- Temperature = 0: Most deterministic, but potentially repetitive\n", - "- Temperature = 1: Balanced creativity and coherence\n", - "- Temperature > 1: Increased randomness, potentially incoherent\n", - "\n", - "A temperature of 1 represents the unscaled probability scores for each token in the vocabulary. Decreasing the temperature closer to 0 sharpens the distribution, so the most likely token will have an even higher probability score. Conversely, increasing the temperature makes the distribution more uniform {cite}`build-llms-from-scratch-book`.\n", - "\n", "In this simple experiment, we use an LLM to write a single-statement executive summary of an input financial filing. We observe that even a simple parameter like temperature can dramatically alter model behavior in ways that are difficult to systematically assess. At temperature 0.0, responses are consistent but potentially too rigid. At 1.0, outputs become more varied but less predictable. At 2.0, responses can be wildly different and often incoherent. This non-deterministic behavior makes traditional software testing approaches inadequate." ] }, @@ -175,6 +176,11 @@ "cell_type": "markdown", "metadata": {}, "source": [ + "A temperature of 1 represents the unscaled probability scores for each token in the vocabulary. Decreasing the temperature closer to 0 sharpens the distribution, so the most likely token will have an even higher probability score. Conversely, increasing the temperature makes the distribution more uniform {cite}`build-llms-from-scratch-book`:\n", + "- Temperature = 0: Most deterministic, but potentially repetitive\n", + "- Temperature = 1: Balanced creativity and coherence\n", + "- Temperature > 1: Increased randomness, potentially incoherent\n", + "\n", "How can one effectively test an LLM-powered system when the same prompt can yield radically different outputs based on a single parameter? Traditional testing relies on predictable inputs and outputs, but LLMs force us to grapple with probabilistic behavior. While lower temperatures may seem safer for critical applications, they don't necessarily eliminate the underlying uncertainty. This highlights the need for new evaluation paradigms that can handle both deterministic and probabilistic aspects of LLM behavior." ] }, @@ -2530,6 +2536,19 @@ "```" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Conclusion\n", + "\n", + "Language models have fundamentally transformed how software is developed and evaluated. Unlike conventional systems that produce predictable outputs, LLMs generate varied, probabilistic responses that defy traditional testing approaches. While developers accustomed to deterministic systems may find this shift challenging, continuing to rely on legacy testing methods is unsustainable. These frameworks were not designed to handle the inherent variability of LLM outputs and will ultimately prove inadequate. \n", + "\n", + "Success requires embracing this new paradigm by implementing comprehensive evaluation strategies early - this is the new Product Requirements Document (PRD) - and cultivating an organizational mindset focused on iteration, experimentation and growth.\n", + "\n", + "The shift from traditional software testing to LLM evaluation is not just a change in tools but a transformation in mindset. Those who recognize and adapt to this shift will lead the way in harnessing the power of LLMs. However, the cost of inaction is not just technological stagnation, but potential business failure." + ] + }, { "cell_type": "markdown", "metadata": {},

              Table 4.6 Comparison of Lighteval, LangSmith, and Promptfoo