add Input chapter to ToC

souzatharsis · Dec 30, 2024 · e52c7a8 · e52c7a8
1 parent 5b39c5d
commit e52c7a8
Show file tree

Hide file tree

Showing 11 changed files with 17 additions and 10 deletions.
diff --git a/tamingllms/_build/.doctrees/environment.pickle b/tamingllms/_build/.doctrees/environment.pickle
diff --git a/tamingllms/_build/.doctrees/markdown/toc.doctree b/tamingllms/_build/.doctrees/markdown/toc.doctree
diff --git a/tamingllms/_build/.doctrees/notebooks/alignment.doctree b/tamingllms/_build/.doctrees/notebooks/alignment.doctree
diff --git a/tamingllms/_build/html/_sources/markdown/toc.md b/tamingllms/_build/html/_sources/markdown/toc.md
@@ -22,7 +22,7 @@ Abstract: *The current discourse around Large Language Models (LLMs) tends to fo
 
 ## [Chapter 1: The Evals Gap](https://www.tamingllms.com/notebooks/evals.html)
 
-## Chapter 2: Managing Input Data
+## [Chapter 2: Managing Input Data](https://www.tamingllms.com/notebooks/input.html)
 
 ## [Chapter 3: Structured Output](https://www.tamingllms.com/notebooks/structured_output.html)
 

diff --git a/tamingllms/_build/html/_sources/notebooks/alignment.ipynb b/tamingllms/_build/html/_sources/notebooks/alignment.ipynb
@@ -261,9 +261,9 @@
     "\\mathcal{L}_{\\text{DPO}}(\\pi_\\theta; \\pi_\\text{ref}) = -\\mathbb{E}_{(x,y_w,y_l) \\sim \\mathcal{D}} \\left[\\log \\sigma \\left(\\beta \\log \\frac{\\pi_\\theta(y_w | x)}{\\pi_\\text{ref}(y_w | x)} - \\beta \\log \\frac{\\pi_\\theta(y_l | x)}{\\pi_\\text{ref}(y_l | x)}\\right)\\right]\n",
     "$$\n",
     "\n",
-    "\n",
-    "\n",
-    "\n",
+    "<!--$$\n",
+    "\\mathcal{L}_{\\text{DPO}}(\\pi_\\theta; \\pi_\\text{ref}) = -\\mathbb{E}_{(x,y_w,y_l) \\sim \\mathcal{D}} \\left[\\log \\sigma \\left(\\beta \\underbrace{\\log \\frac{\\pi_\\theta(y_w | x)}{\\pi_\\text{ref}(y_w | x)}}_{\\color{green}\\text{preferred}} - \\beta \\underbrace{\\log \\frac{\\pi_\\theta(y_l | x)}{\\pi_\\text{ref}(y_l | x)}}_{\\color{red}\\text{rejected}}\\right)\\right]\n",
+    "$$-->\n",
     "\n",
     "where, \n",
     "- $\\pi_\\theta$ represents the language model,\n",

diff --git a/tamingllms/_build/html/markdown/toc.html b/tamingllms/_build/html/markdown/toc.html
@@ -249,7 +249,7 @@ <h2><a class="reference external" href="https://www.tamingllms.com/markdown/intr
 <h2><a class="reference external" href="https://www.tamingllms.com/notebooks/evals.html">Chapter 1: The Evals Gap</a><a class="headerlink" href="#chapter-1-the-evals-gap" title="Permalink to this heading">¶</a></h2>
 </section>
 <section id="chapter-2-managing-input-data">
-<h2>Chapter 2: Managing Input Data<a class="headerlink" href="#chapter-2-managing-input-data" title="Permalink to this heading">¶</a></h2>
+<h2><a class="reference external" href="https://www.tamingllms.com/notebooks/input.html">Chapter 2: Managing Input Data</a><a class="headerlink" href="#chapter-2-managing-input-data" title="Permalink to this heading">¶</a></h2>
 </section>
 <section id="chapter-3-structured-output">
 <h2><a class="reference external" href="https://www.tamingllms.com/notebooks/structured_output.html">Chapter 3: Structured Output</a><a class="headerlink" href="#chapter-3-structured-output" title="Permalink to this heading">¶</a></h2>

diff --git a/tamingllms/_build/html/notebooks/alignment.html b/tamingllms/_build/html/notebooks/alignment.html
@@ -497,6 +497,9 @@ <h4><a class="toc-backref" href="#id255" role="doc-backlink"><span class="sectio
 \[
 \mathcal{L}_{\text{DPO}}(\pi_\theta; \pi_\text{ref}) = -\mathbb{E}_{(x,y_w,y_l) \sim \mathcal{D}} \left[\log \sigma \left(\beta \log \frac{\pi_\theta(y_w | x)}{\pi_\text{ref}(y_w | x)} - \beta \log \frac{\pi_\theta(y_l | x)}{\pi_\text{ref}(y_l | x)}\right)\right]
 \]</div>
+<!--$$
+\mathcal{L}_{\text{DPO}}(\pi_\theta; \pi_\text{ref}) = -\mathbb{E}_{(x,y_w,y_l) \sim \mathcal{D}} \left[\log \sigma \left(\beta \underbrace{\log \frac{\pi_\theta(y_w | x)}{\pi_\text{ref}(y_w | x)}}_{\color{green}\text{preferred}} - \beta \underbrace{\log \frac{\pi_\theta(y_l | x)}{\pi_\text{ref}(y_l | x)}}_{\color{red}\text{rejected}}\right)\right]
+$$-->
 <p>where,</p>
 <ul class="simple">
 <li><p><span class="math notranslate nohighlight">\(\pi_\theta\)</span> represents the language model,</p></li>

diff --git 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": "05386e77",
+   "id": "7fc6bb1a",
    "metadata": {},
    "source": [
     "(intro)=\n",

diff --git a/tamingllms/_build/jupyter_execute/notebooks/alignment.ipynb b/tamingllms/_build/jupyter_execute/notebooks/alignment.ipynb
@@ -261,9 +261,9 @@
     "\\mathcal{L}_{\\text{DPO}}(\\pi_\\theta; \\pi_\\text{ref}) = -\\mathbb{E}_{(x,y_w,y_l) \\sim \\mathcal{D}} \\left[\\log \\sigma \\left(\\beta \\log \\frac{\\pi_\\theta(y_w | x)}{\\pi_\\text{ref}(y_w | x)} - \\beta \\log \\frac{\\pi_\\theta(y_l | x)}{\\pi_\\text{ref}(y_l | x)}\\right)\\right]\n",
     "$$\n",
     "\n",
-    "\n",
-    "\n",
-    "\n",
+    "<!--$$\n",
+    "\\mathcal{L}_{\\text{DPO}}(\\pi_\\theta; \\pi_\\text{ref}) = -\\mathbb{E}_{(x,y_w,y_l) \\sim \\mathcal{D}} \\left[\\log \\sigma \\left(\\beta \\underbrace{\\log \\frac{\\pi_\\theta(y_w | x)}{\\pi_\\text{ref}(y_w | x)}}_{\\color{green}\\text{preferred}} - \\beta \\underbrace{\\log \\frac{\\pi_\\theta(y_l | x)}{\\pi_\\text{ref}(y_l | x)}}_{\\color{red}\\text{rejected}}\\right)\\right]\n",
+    "$$-->\n",
     "\n",
     "where, \n",
     "- $\\pi_\\theta$ represents the language model,\n",

diff --git a/tamingllms/markdown/toc.md b/tamingllms/markdown/toc.md
@@ -22,7 +22,7 @@ Abstract: *The current discourse around Large Language Models (LLMs) tends to fo
 
 ## [Chapter 1: The Evals Gap](https://www.tamingllms.com/notebooks/evals.html)
 
-## Chapter 2: Managing Input Data
+## [Chapter 2: Managing Input Data](https://www.tamingllms.com/notebooks/input.html)
 
 ## [Chapter 3: Structured Output](https://www.tamingllms.com/notebooks/structured_output.html)
 

diff --git a/tamingllms/notebooks/alignment.ipynb b/tamingllms/notebooks/alignment.ipynb
@@ -261,6 +261,10 @@
     "\\mathcal{L}_{\\text{DPO}}(\\pi_\\theta; \\pi_\\text{ref}) = -\\mathbb{E}_{(x,y_w,y_l) \\sim \\mathcal{D}} \\left[\\log \\sigma \\left(\\beta \\log \\frac{\\pi_\\theta(y_w | x)}{\\pi_\\text{ref}(y_w | x)} - \\beta \\log \\frac{\\pi_\\theta(y_l | x)}{\\pi_\\text{ref}(y_l | x)}\\right)\\right]\n",
     "$$\n",
     "\n",
+    "<!--$$\n",
+    "\\mathcal{L}_{\\text{DPO}}(\\pi_\\theta; \\pi_\\text{ref}) = -\\mathbb{E}_{(x,y_w,y_l) \\sim \\mathcal{D}} \\left[\\log \\sigma \\left(\\beta \\underbrace{\\log \\frac{\\pi_\\theta(y_w | x)}{\\pi_\\text{ref}(y_w | x)}}_{\\color{green}\\text{preferred}} - \\beta \\underbrace{\\log \\frac{\\pi_\\theta(y_l | x)}{\\pi_\\text{ref}(y_l | x)}}_{\\color{red}\\text{rejected}}\\right)\\right]\n",
+    "$$-->\n",
+    "\n",
     "where, \n",
     "- $\\pi_\\theta$ represents the language model,\n",
     "- $\\pi_{ref}$ represents the reference model,\n",