Files
ais-llm-quantization-project/QuantizeTinyLLama.ipynb

351 lines
21 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "bc2d31ca-c7c0-4720-810a-1bb08feff62c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting torch\n",
" Downloading torch-2.7.1-cp311-none-macosx_11_0_arm64.whl.metadata (29 kB)\n",
"Collecting filelock (from torch)\n",
" Downloading filelock-3.18.0-py3-none-any.whl.metadata (2.9 kB)\n",
"Requirement already satisfied: typing-extensions>=4.10.0 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from torch) (4.12.2)\n",
"Collecting sympy>=1.13.3 (from torch)\n",
" Downloading sympy-1.14.0-py3-none-any.whl.metadata (12 kB)\n",
"Collecting networkx (from torch)\n",
" Downloading networkx-3.5-py3-none-any.whl.metadata (6.3 kB)\n",
"Requirement already satisfied: jinja2 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from torch) (3.1.6)\n",
"Collecting fsspec (from torch)\n",
" Downloading fsspec-2025.7.0-py3-none-any.whl.metadata (12 kB)\n",
"Collecting mpmath<1.4,>=1.1.0 (from sympy>=1.13.3->torch)\n",
" Downloading mpmath-1.3.0-py3-none-any.whl.metadata (8.6 kB)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from jinja2->torch) (3.0.2)\n",
"Downloading torch-2.7.1-cp311-none-macosx_11_0_arm64.whl (68.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m68.6/68.6 MB\u001b[0m \u001b[31m11.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading sympy-1.14.0-py3-none-any.whl (6.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.3/6.3 MB\u001b[0m \u001b[31m11.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m \u001b[36m0:00:01\u001b[0mm\n",
"\u001b[?25hDownloading mpmath-1.3.0-py3-none-any.whl (536 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m536.2/536.2 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading filelock-3.18.0-py3-none-any.whl (16 kB)\n",
"Downloading fsspec-2025.7.0-py3-none-any.whl (199 kB)\n",
"Downloading networkx-3.5-py3-none-any.whl (2.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m11.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hInstalling collected packages: mpmath, sympy, networkx, fsspec, filelock, torch\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6/6\u001b[0m [torch]32m5/6\u001b[0m [torch]]x]\n",
"\u001b[1A\u001b[2KSuccessfully installed filelock-3.18.0 fsspec-2025.7.0 mpmath-1.3.0 networkx-3.5 sympy-1.14.0 torch-2.7.1\n"
]
}
],
"source": [
"!pip install torch "
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f65e39b7-54d9-4577-8cc2-64d94339b362",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting transformers\n",
" Downloading transformers-4.53.2-py3-none-any.whl.metadata (40 kB)\n",
"Requirement already satisfied: filelock in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from transformers) (3.18.0)\n",
"Collecting huggingface-hub<1.0,>=0.30.0 (from transformers)\n",
" Downloading huggingface_hub-0.33.4-py3-none-any.whl.metadata (14 kB)\n",
"Requirement already satisfied: numpy>=1.17 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from transformers) (1.26.4)\n",
"Requirement already satisfied: packaging>=20.0 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from transformers) (25.0)\n",
"Requirement already satisfied: pyyaml>=5.1 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from transformers) (6.0.2)\n",
"Collecting regex!=2019.12.17 (from transformers)\n",
" Downloading regex-2024.11.6-cp311-cp311-macosx_11_0_arm64.whl.metadata (40 kB)\n",
"Requirement already satisfied: requests in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from transformers) (2.32.4)\n",
"Collecting tokenizers<0.22,>=0.21 (from transformers)\n",
" Downloading tokenizers-0.21.2-cp39-abi3-macosx_11_0_arm64.whl.metadata (6.8 kB)\n",
"Collecting safetensors>=0.4.3 (from transformers)\n",
" Downloading safetensors-0.5.3-cp38-abi3-macosx_11_0_arm64.whl.metadata (3.8 kB)\n",
"Collecting tqdm>=4.27 (from transformers)\n",
" Downloading tqdm-4.67.1-py3-none-any.whl.metadata (57 kB)\n",
"Requirement already satisfied: fsspec>=2023.5.0 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from huggingface-hub<1.0,>=0.30.0->transformers) (2025.7.0)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from huggingface-hub<1.0,>=0.30.0->transformers) (4.12.2)\n",
"Collecting hf-xet<2.0.0,>=1.1.2 (from huggingface-hub<1.0,>=0.30.0->transformers)\n",
" Downloading hf_xet-1.1.5-cp37-abi3-macosx_11_0_arm64.whl.metadata (879 bytes)\n",
"Requirement already satisfied: charset_normalizer<4,>=2 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from requests->transformers) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from requests->transformers) (3.7)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from requests->transformers) (2.5.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages (from requests->transformers) (2025.7.14)\n",
"Downloading transformers-4.53.2-py3-none-any.whl (10.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.8/10.8 MB\u001b[0m \u001b[31m11.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading huggingface_hub-0.33.4-py3-none-any.whl (515 kB)\n",
"Downloading hf_xet-1.1.5-cp37-abi3-macosx_11_0_arm64.whl (2.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.6/2.6 MB\u001b[0m \u001b[31m9.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading tokenizers-0.21.2-cp39-abi3-macosx_11_0_arm64.whl (2.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.7/2.7 MB\u001b[0m \u001b[31m11.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading regex-2024.11.6-cp311-cp311-macosx_11_0_arm64.whl (284 kB)\n",
"Downloading safetensors-0.5.3-cp38-abi3-macosx_11_0_arm64.whl (418 kB)\n",
"Downloading tqdm-4.67.1-py3-none-any.whl (78 kB)\n",
"Installing collected packages: tqdm, safetensors, regex, hf-xet, huggingface-hub, tokenizers, transformers\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7/7\u001b[0m [transformers][0m [transformers]ub]\n",
"\u001b[1A\u001b[2KSuccessfully installed hf-xet-1.1.5 huggingface-hub-0.33.4 regex-2024.11.6 safetensors-0.5.3 tokenizers-0.21.2 tqdm-4.67.1 transformers-4.53.2\n"
]
}
],
"source": [
"!pip install transformers"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "179a4065-ff16-40b0-a2ee-fa81f056702f",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/anaconda3/envs/quantizeEnv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"4.53.2\n"
]
}
],
"source": [
"import transformers\n",
"\n",
"print(transformers.__version__)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "51eeda48-a98a-4e19-a403-98c4a90936ff",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2.7.1\n"
]
}
],
"source": [
"import torch \n",
"print(torch.__version__)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "c711bdc4-06c7-4492-ade8-ab3497cb5dcf",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting git+https://github.com/Vahe1994/SpQR.git\n",
" Cloning https://github.com/Vahe1994/SpQR.git to /private/var/folders/x9/myx7g6t11gv0dghwblns7qww0000gn/T/pip-req-build-yrjhb217\n",
" Running command git clone --filter=blob:none --quiet https://github.com/Vahe1994/SpQR.git /private/var/folders/x9/myx7g6t11gv0dghwblns7qww0000gn/T/pip-req-build-yrjhb217\n",
" Resolved https://github.com/Vahe1994/SpQR.git to commit 902abdb012b24b07d0f4376bdc46952e4189add1\n",
" Installing build dependencies ... \u001b[?25ldone\n",
"\u001b[?25h Getting requirements to build wheel ... \u001b[?25lerror\n",
" \u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n",
" \n",
" \u001b[31m×\u001b[0m \u001b[32mGetting requirements to build wheel\u001b[0m did not run successfully.\n",
" \u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n",
" \u001b[31m╰─>\u001b[0m \u001b[31m[14 lines of output]\u001b[0m\n",
" \u001b[31m \u001b[0m error: Multiple top-level packages discovered in a flat-layout: ['data', 'inference_lib'].\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m To avoid accidental inclusion of unwanted files or directories,\n",
" \u001b[31m \u001b[0m setuptools will not proceed with this build.\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m If you are trying to create a single distribution with multiple packages\n",
" \u001b[31m \u001b[0m on purpose, you should not rely on automatic discovery.\n",
" \u001b[31m \u001b[0m Instead, consider the following options:\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m 1. set up custom discovery (`find` directive with `include` or `exclude`)\n",
" \u001b[31m \u001b[0m 2. use a `src-layout`\n",
" \u001b[31m \u001b[0m 3. explicitly set `py_modules` or `packages` with a list of names\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m To find more information, look for \"package discovery\" on setuptools docs.\n",
" \u001b[31m \u001b[0m \u001b[31m[end of output]\u001b[0m\n",
" \n",
" \u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n",
"\u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n",
"\n",
"\u001b[31m×\u001b[0m \u001b[32mGetting requirements to build wheel\u001b[0m did not run successfully.\n",
"\u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n",
"\u001b[31m╰─>\u001b[0m See above for output.\n",
"\n",
"\u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n",
"\u001b[?25h"
]
}
],
"source": [
"!pip install git+https://github.com/Vahe1994/SpQR.git"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "80983f78-45f4-48a4-9749-592c635eff05",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting git+https://github.com/Vahe1994/SpQR.git\n",
" Cloning https://github.com/Vahe1994/SpQR.git to /private/var/folders/x9/myx7g6t11gv0dghwblns7qww0000gn/T/pip-req-build-8n1i0qes\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" Running command git clone --filter=blob:none --quiet https://github.com/Vahe1994/SpQR.git /private/var/folders/x9/myx7g6t11gv0dghwblns7qww0000gn/T/pip-req-build-8n1i0qes\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" Resolved https://github.com/Vahe1994/SpQR.git to commit 902abdb012b24b07d0f4376bdc46952e4189add1\n",
" Installing build dependencies: started\n",
" Installing build dependencies: finished with status 'done'\n",
" Getting requirements to build wheel: started\n",
" Getting requirements to build wheel: finished with status 'error'\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" \u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n",
" \n",
" \u001b[31m×\u001b[0m \u001b[32mGetting requirements to build wheel\u001b[0m did not run successfully.\n",
" \u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n",
" \u001b[31m╰─>\u001b[0m \u001b[31m[14 lines of output]\u001b[0m\n",
" \u001b[31m \u001b[0m error: Multiple top-level packages discovered in a flat-layout: ['data', 'inference_lib'].\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m To avoid accidental inclusion of unwanted files or directories,\n",
" \u001b[31m \u001b[0m setuptools will not proceed with this build.\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m If you are trying to create a single distribution with multiple packages\n",
" \u001b[31m \u001b[0m on purpose, you should not rely on automatic discovery.\n",
" \u001b[31m \u001b[0m Instead, consider the following options:\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m 1. set up custom discovery (`find` directive with `include` or `exclude`)\n",
" \u001b[31m \u001b[0m 2. use a `src-layout`\n",
" \u001b[31m \u001b[0m 3. explicitly set `py_modules` or `packages` with a list of names\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m To find more information, look for \"package discovery\" on setuptools docs.\n",
" \u001b[31m \u001b[0m \u001b[31m[end of output]\u001b[0m\n",
" \n",
" \u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n",
"\u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n",
"\n",
"\u001b[31m×\u001b[0m \u001b[32mGetting requirements to build wheel\u001b[0m did not run successfully.\n",
"\u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n",
"\u001b[31m╰─>\u001b[0m See above for output.\n",
"\n",
"\u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n"
]
},
{
"ename": "CalledProcessError",
"evalue": "Command '['/opt/anaconda3/envs/quantizeEnv/bin/python', '-m', 'pip', 'install', 'git+https://github.com/Vahe1994/SpQR.git']' returned non-zero exit status 1.",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mModuleNotFoundError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[6]\u001b[39m\u001b[32m, line 4\u001b[39m\n\u001b[32m 3\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m----> \u001b[39m\u001b[32m4\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mspqr\u001b[39;00m\n\u001b[32m 5\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m:\n",
"\u001b[31mModuleNotFoundError\u001b[39m: No module named 'spqr'",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[31mCalledProcessError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[6]\u001b[39m\u001b[32m, line 6\u001b[39m\n\u001b[32m 4\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mspqr\u001b[39;00m\n\u001b[32m 5\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m:\n\u001b[32m----> \u001b[39m\u001b[32m6\u001b[39m subprocess.check_call([sys.executable, \u001b[33m\"\u001b[39m\u001b[33m-m\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mpip\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33minstall\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mgit+https://github.com/Vahe1994/SpQR.git\u001b[39m\u001b[33m\"\u001b[39m])\n",
"\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/quantizeEnv/lib/python3.11/subprocess.py:413\u001b[39m, in \u001b[36mcheck_call\u001b[39m\u001b[34m(*popenargs, **kwargs)\u001b[39m\n\u001b[32m 411\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m cmd \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[32m 412\u001b[39m cmd = popenargs[\u001b[32m0\u001b[39m]\n\u001b[32m--> \u001b[39m\u001b[32m413\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m CalledProcessError(retcode, cmd)\n\u001b[32m 414\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[32m0\u001b[39m\n",
"\u001b[31mCalledProcessError\u001b[39m: Command '['/opt/anaconda3/envs/quantizeEnv/bin/python', '-m', 'pip', 'install', 'git+https://github.com/Vahe1994/SpQR.git']' returned non-zero exit status 1."
]
}
],
"source": [
"import subprocess, sys\n",
"\n",
"try:\n",
" import spqr\n",
"except ImportError:\n",
" subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"git+https://github.com/Vahe1994/SpQR.git\"])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "ec5aff0e-e93f-4150-b6e4-7365aa733b99",
"metadata": {},
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'spqr'",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mModuleNotFoundError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[5]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mspqr\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m quantize_model\n\u001b[32m 2\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mtransformers\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m AutoModelForCausalLM, AutoTokenizer\n\u001b[32m 3\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mhuggingface_hub\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m snapshot_download\n",
"\u001b[31mModuleNotFoundError\u001b[39m: No module named 'spqr'"
]
}
],
"source": [
"from spqr import quantize_model\n",
"from transformers import AutoModelForCausalLM, AutoTokenizer\n",
"from huggingface_hub import snapshot_download"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "543f0bf8-af85-4c97-9e85-4d248a618409",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}