update numbers

OSU-NLP-Group · Feb 20, 2024 · 99f645f · 99f645f
1 parent 640b156
commit 99f645f
Show file tree

Hide file tree

Showing 2 changed files with 175 additions and 1 deletion.
diff --git a/index.html b/index.html
@@ -266,7 +266,7 @@ <h2 class="subtitle is-3 publication-subtitle">
             demonstrate
             that our developed LLMs can achieve very strong results on a comprehensive set of chemistry tasks,
             <i>outperforming the most advanced GPT-4 across all the tasks by a substantial margin
-              <strong>(e.g., 94.5% exact match for converting SMILES to Formula vs. GPT-4's 16.4%;
+              <strong>(e.g., 94.5% exact match for converting SMILES to Formula vs. GPT-4's 16.4%; 
                 32.9% exact match for Retrosynthesis vs. GPT-4's 1.2%)</strong> and approaching the SoTA task-specific
               models.</i>
             The key to our success is a large-scale, comprehensive, high-quality dataset for instruction tuning named

diff --git a/test_generation.ipynb b/test_generation.ipynb
@@ -0,0 +1,174 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "===================================BUG REPORT===================================\n",
+      "Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
+      "================================================================================\n",
+      "CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64...\n",
+      "CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so\n",
+      "CUDA SETUP: Highest compute capability among GPUs detected: 8.6\n",
+      "CUDA SETUP: Detected CUDA version 118\n",
+      "CUDA SETUP: Loading binary /home/yu.3737/Software/miniconda3/envs/lora/lib/python3.9/site-packages/bitsandbytes/libbitsandbytes_cuda118.so...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/yu.3737/Software/miniconda3/envs/lora/lib/python3.9/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: /home/yu.3737/Software/miniconda3/envs/lora did not contain libcudart.so as expected! Searching further paths...\n",
+      "  warn(msg)\n",
+      "/home/yu.3737/Software/miniconda3/envs/lora/lib/python3.9/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('FILE')}\n",
+      "  warn(msg)\n",
+      "/home/yu.3737/Software/miniconda3/envs/lora/lib/python3.9/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/modulefiles')}\n",
+      "  warn(msg)\n",
+      "/home/yu.3737/Software/miniconda3/envs/lora/lib/python3.9/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/share/lmod/lmod/share/man')}\n",
+      "  warn(msg)\n",
+      "/home/yu.3737/Software/miniconda3/envs/lora/lib/python3.9/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('() {  eval $($LMOD_DIR/ml_cmd \"$@\")\\n}')}\n",
+      "  warn(msg)\n",
+      "/home/yu.3737/Software/miniconda3/envs/lora/lib/python3.9/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('vs/workbench/api/node/extensionHostProcess')}\n",
+      "  warn(msg)\n",
+      "/home/yu.3737/Software/miniconda3/envs/lora/lib/python3.9/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//matplotlib_inline.backend_inline'), PosixPath('module')}\n",
+      "  warn(msg)\n"
+     ]
+    }
+   ],
+   "source": [
+    "from generation import LlaSMolGeneration, canonicalize_smiles_in_text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "91482b88007548129672708d278f7f09",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "generator = LlaSMolGeneration('osunlp/LlaSMol-Mistral-7B')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'input_text': 'Given the SMILES representation <SMILES> S=P1(N(CCCl)CCCl)NCCCO1 </SMILES>, what would be its molecular formula?',\n",
+       "  'real_input_text': '<s>[INST] Given the SMILES representation <SMILES> S=P1(N(CCCl)CCCl)NCCCO1 </SMILES> , what would be its molecular formula? [/INST]',\n",
+       "  'output': ['It is <MOLFORMULA> C7H15Cl2N2OPS </MOLFORMULA> . </s>']}]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "generator.generate(\n",
+    "    'Given the SMILES representation <SMILES> S=P1(N(CCCl)CCCl)NCCCO1 </SMILES>, what would be its molecular formula?'\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from utils.smiles_canonicalization import canonicalize_molecule_smiles"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'CCC1(C)CCOC1=O'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "canonicalize_molecule_smiles('CCC1(C)CCOC1=O')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'CCC1(C)COC(=O)C1'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "canonicalize_molecule_smiles('CCC1(C)COC(=O)C1')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "lora",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}