├── aia-activity-rag.csv ├── README.md ├── .gitignore ├── Llama-2-example.ipynb ├── LICENSE ├── demo-3-Mistral_7b_FastAPI_Service_Colab_Example_External_Version_v2.ipynb ├── Llama_2_FastAPI_Service_Colab_Example.ipynb └── demo-1-llama_gguf_prediction.ipynb /aia-activity-rag.csv: -------------------------------------------------------------------------------- 1 | data 2 | 台灣人工智慧共識協作工作坊 - AI & Web3 專場 3 | 日期：2023/12/10（日） 4 | 時間：13:00 - 17:00 5 | 地點：松菸 W210 西向會議室 6 | 主辦：台灣人工智慧學校、moda 數位發展部 及 da0 7 | 協辦：Funding the Commons、 AIT 美國在台協會、美國創新中心 AIC 及 松菸創作者工廠 8 | 報名網址：https://forms.gle/gGQk1Ay1suWpf6pQ9 9 | "活動議程： 10 | 13:00-13:30 報到 11 | 13:30-13:40 開場短講(侯宜秀律師) 12 | 13:40-14:20 盤點 AI 目前衝擊跟擔憂 13 | 14:20-14:35 中場休息 14 | 14:35-15:25 盤點針對 AI 衝擊的 web3 解法 15 | 15:25-15:35 中場休息 16 | 15:35-15:50 a16z AIxWeb3 報告摘要(Noah Yeh) 17 | 15:50-16:30 覆盤 Web3 的解法真的可以解決問題嗎？ 18 | 16:30-16:40 活動總回顧 10min" 19 | "備註： 20 | 本場活動將遵守「Chatham House Rule」紀錄活動過程產出。如果一個會議，或會議的一部分，是按照Chatham House規則進行的，則與會者可自由使用在會議中獲得的資訊，但不得透露演講者及其他與會者的身份與所屬機構。" -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Llama-2-cpp-example 2 | An example to run Llama 2 cpp python in Colab environment. 3 | 4 | # Link: 5 | 6 | Part 1: How to use llama 2 7 | Colab Link: [Link](https://colab.research.google.com/github/LiuYuWei/Llama-2-cpp-example/blob/main/Llama-2-example.ipynb) 8 | 9 | Part 2: How to let llama 2 Model as a Fastapi Service 10 | Colab Link: [Link](https://colab.research.google.com/github/LiuYuWei/Llama-2-cpp-example/blob/main/Llama_2_FastAPI_Service_Colab_Example.ipynb) 11 | 12 | Part 3: How to let mistral 7b Model as a Fastapi Service 13 | Colab Link: [Link](https://colab.research.google.com/github/LiuYuWei/Llama-2-cpp-example/blob/main/Mistral_7b_FastAPI_Service_Colab_Example_External_Version.ipynb) 14 | 15 | # Course: 16 | 17 | - Demo 1 - GGUF example code: 18 | Colab Link: [Link](https://colab.research.google.com/github/LiuYuWei/Llama-2-cpp-example/blob/main/demo-1-llama_gguf_prediction.ipynb) 19 | 20 | - Demo 2 - Embedding Vector and RAG: 21 | Colab Link: [Link](https://colab.research.google.com/github/LiuYuWei/Llama-2-cpp-example/blob/main/demo-2-rag_example.ipynb) 22 | 23 | - Demo 3 - Let mistral 7b Model as a Fastapi Service 24 | Colab Link: [Link](https://colab.research.google.com/github/LiuYuWei/Llama-2-cpp-example/blob/main/demo-3-Mistral_7b_FastAPI_Service_Colab_Example_External_Version_v2.ipynb) 25 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | -------------------------------------------------------------------------------- /Llama-2-example.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "id": "bba801bf", 6 | "metadata": {}, 7 | "source": [ 8 | "# Llama 2 Introduction\n", 9 | "\n", 10 | "#### Made by SimonLiu\n", 11 | "\n", 12 | "1. My Linkedin: https://www.linkedin.com/in/simonliuyuwei/\n", 13 | "\n", 14 | "2. InfuseAI: https://infuseai.io" 15 | ] 16 | }, 17 | { 18 | "cell_type": "markdown", 19 | "id": "668cc076", 20 | "metadata": {}, 21 | "source": [ 22 | "### Llama 2\n", 23 | "\n", 24 | "The next generation of our open source large language model\n", 25 | "\n", 26 | "1. Official Website: [Link](https://ai.meta.com/llama/)\n", 27 | "\n", 28 | "2. Download Model: [Link](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)" 29 | ] 30 | }, 31 | { 32 | "cell_type": "markdown", 33 | "id": "617852d9", 34 | "metadata": {}, 35 | "source": [ 36 | "### Related Website: \n", 37 | "\n", 38 | "1. llama.cpp: [Link](https://github.com/ggerganov/llama.cpp)\n", 39 | "\n", 40 | "2. llama-cpp-python: [Link](https://github.com/abetlen/llama-cpp-python)\n", 41 | "\n", 42 | "3. ggml: Tensor library for machine learning - [Link](https://github.com/ggerganov/ggml)" 43 | ] 44 | }, 45 | { 46 | "cell_type": "markdown", 47 | "id": "3a7a1d72", 48 | "metadata": {}, 49 | "source": [ 50 | "# Code" 51 | ] 52 | }, 53 | { 54 | "cell_type": "markdown", 55 | "id": "cd34727e", 56 | "metadata": {}, 57 | "source": [ 58 | "## Step 1: Install related package" 59 | ] 60 | }, 61 | { 62 | "cell_type": "code", 63 | "execution_count": null, 64 | "id": "b97cf78b", 65 | "metadata": {}, 66 | "outputs": [], 67 | "source": [ 68 | "# GPU llama-cpp-python\n", 69 | "!CMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" FORCE_CMAKE=1 pip install llama-cpp-python --force-reinstall --upgrade --no-cache-dir --verbose" 70 | ] 71 | }, 72 | { 73 | "cell_type": "code", 74 | "execution_count": null, 75 | "id": "8b334357", 76 | "metadata": {}, 77 | "outputs": [], 78 | "source": [ 79 | "# For download the models\n", 80 | "!pip install huggingface_hub" 81 | ] 82 | }, 83 | { 84 | "cell_type": "markdown", 85 | "id": "b617a2d2", 86 | "metadata": {}, 87 | "source": [ 88 | "## Step 2: Import python libraries and Variable config" 89 | ] 90 | }, 91 | { 92 | "cell_type": "markdown", 93 | "id": "33bb302a", 94 | "metadata": {}, 95 | "source": [ 96 | "### Import Python Package" 97 | ] 98 | }, 99 | { 100 | "cell_type": "code", 101 | "execution_count": null, 102 | "id": "c138f0cd", 103 | "metadata": {}, 104 | "outputs": [], 105 | "source": [ 106 | "from huggingface_hub import hf_hub_download\n", 107 | "from llama_cpp import Llama" 108 | ] 109 | }, 110 | { 111 | "cell_type": "markdown", 112 | "id": "4a79589c", 113 | "metadata": {}, 114 | "source": [ 115 | "### Configure Variables" 116 | ] 117 | }, 118 | { 119 | "cell_type": "code", 120 | "execution_count": null, 121 | "id": "f2eaa426", 122 | "metadata": {}, 123 | "outputs": [], 124 | "source": [ 125 | "download_model_bool = True" 126 | ] 127 | }, 128 | { 129 | "cell_type": "markdown", 130 | "id": "0b6e85ad", 131 | "metadata": {}, 132 | "source": [ 133 | "#### HuggingFace Llama-cpp Model Link:\n", 134 | "\n", 135 | "1. TheBloke/Llama-2-7B-chat-GGML: [Link](https://huggingface.co/TheBloke/Llama-2-7B-chat-GGML)\n", 136 | "2. TheBloke/Llama-2-13B-chat-GGML: [Link](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML)\n", 137 | "3. TheBloke/Llama-2-70B-chat-GGML: [Link](https://huggingface.co/TheBloke/Llama-2-70B-chat-GGML)\n", 138 | "4. audreyt/Taiwan-LLaMa-v1.0-GGML: [Link](https://huggingface.co/audreyt/Taiwan-LLaMa-v1.0-GGML)" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "id": "0d430952", 145 | "metadata": {}, 146 | "outputs": [], 147 | "source": [ 148 | "model_name_or_path = \"TheBloke/Llama-2-13B-chat-GGML\"" 149 | ] 150 | }, 151 | { 152 | "cell_type": "markdown", 153 | "id": "514dfe3b", 154 | "metadata": {}, 155 | "source": [ 156 | "#### the model is in bin format:\n", 157 | "Please Get the bin file from here: https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/tree/main" 158 | ] 159 | }, 160 | { 161 | "cell_type": "code", 162 | "execution_count": null, 163 | "id": "2657226c", 164 | "metadata": {}, 165 | "outputs": [], 166 | "source": [ 167 | "model_basename = \"llama-2-13b-chat.ggmlv3.q5_1.bin\"" 168 | ] 169 | }, 170 | { 171 | "cell_type": "markdown", 172 | "id": "c54db323", 173 | "metadata": {}, 174 | "source": [ 175 | "## Step 3: Download Model" 176 | ] 177 | }, 178 | { 179 | "cell_type": "code", 180 | "execution_count": null, 181 | "id": "920b26e6", 182 | "metadata": {}, 183 | "outputs": [], 184 | "source": [ 185 | "model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)" 186 | ] 187 | }, 188 | { 189 | "cell_type": "code", 190 | "execution_count": null, 191 | "id": "cad8e269", 192 | "metadata": {}, 193 | "outputs": [], 194 | "source": [ 195 | "print(model_path)" 196 | ] 197 | }, 198 | { 199 | "cell_type": "markdown", 200 | "id": "17c2c078", 201 | "metadata": {}, 202 | "source": [ 203 | "## Step 4: Loading the Model" 204 | ] 205 | }, 206 | { 207 | "cell_type": "code", 208 | "execution_count": null, 209 | "id": "e62c50a3", 210 | "metadata": {}, 211 | "outputs": [], 212 | "source": [ 213 | "# GPU\n", 214 | "lcpp_llm = None\n", 215 | "lcpp_llm = Llama(\n", 216 | " model_path=model_path,\n", 217 | " n_threads=2, # CPU cores\n", 218 | " n_batch=512, # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.\n", 219 | " n_gpu_layers=32 # Change this value based on your model and your GPU VRAM pool.\n", 220 | ")" 221 | ] 222 | }, 223 | { 224 | "cell_type": "markdown", 225 | "id": "c235c196", 226 | "metadata": {}, 227 | "source": [ 228 | "## Step 5: Create a Prompt" 229 | ] 230 | }, 231 | { 232 | "cell_type": "code", 233 | "execution_count": null, 234 | "id": "24d261b8", 235 | "metadata": {}, 236 | "outputs": [], 237 | "source": [ 238 | "prompt = \"Write a linear regression in python\"" 239 | ] 240 | }, 241 | { 242 | "cell_type": "code", 243 | "execution_count": null, 244 | "id": "9764a441", 245 | "metadata": {}, 246 | "outputs": [], 247 | "source": [ 248 | "prompt_template=f'''SYSTEM: You are a helpful, respectful and honest assistant. Always answer as helpfully.\n", 249 | "\n", 250 | "USER: {prompt}\n", 251 | "\n", 252 | "ASSISTANT:\n", 253 | "'''" 254 | ] 255 | }, 256 | { 257 | "cell_type": "markdown", 258 | "id": "1bcf7cb2", 259 | "metadata": {}, 260 | "source": [ 261 | "## Step 6: Generating the Response" 262 | ] 263 | }, 264 | { 265 | "cell_type": "code", 266 | "execution_count": null, 267 | "id": "879a2c22", 268 | "metadata": {}, 269 | "outputs": [], 270 | "source": [ 271 | "# Predict the Result\n", 272 | "response = lcpp_llm(prompt=prompt_template, max_tokens=256, temperature=0.5, top_p=0.95,\n", 273 | " repeat_penalty=1.2, top_k=150,\n", 274 | " echo=True)" 275 | ] 276 | }, 277 | { 278 | "cell_type": "code", 279 | "execution_count": null, 280 | "id": "0b6506b1", 281 | "metadata": {}, 282 | "outputs": [], 283 | "source": [ 284 | "# Print the json content.\n", 285 | "response" 286 | ] 287 | }, 288 | { 289 | "cell_type": "code", 290 | "execution_count": null, 291 | "id": "8a4f367d", 292 | "metadata": {}, 293 | "outputs": [], 294 | "source": [ 295 | "# Print the response answer.\n", 296 | "print(response[\"choices\"][0][\"text\"])" 297 | ] 298 | } 299 | ], 300 | "metadata": { 301 | "kernelspec": { 302 | "display_name": "Python 3 (ipykernel)", 303 | "language": "python", 304 | "name": "python3" 305 | }, 306 | "language_info": { 307 | "codemirror_mode": { 308 | "name": "ipython", 309 | "version": 3 310 | }, 311 | "file_extension": ".py", 312 | "mimetype": "text/x-python", 313 | "name": "python", 314 | "nbconvert_exporter": "python", 315 | "pygments_lexer": "ipython3", 316 | "version": "3.7.12" 317 | } 318 | }, 319 | "nbformat": 4, 320 | "nbformat_minor": 5 321 | } 322 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /demo-3-Mistral_7b_FastAPI_Service_Colab_Example_External_Version_v2.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": { 6 | "id": "VUC9Opfd8Mpt" 7 | }, 8 | "source": [ 9 | "# Llama 2 Fastapi Service Example" 10 | ] 11 | }, 12 | { 13 | "cell_type": "markdown", 14 | "metadata": { 15 | "id": "e9e9QOWD-l7k" 16 | }, 17 | "source": [ 18 | "推薦至少使用 T4 GPU 來作為你的服務啟用" 19 | ] 20 | }, 21 | { 22 | "cell_type": "markdown", 23 | "metadata": { 24 | "id": "h4zPTxsL7rUn" 25 | }, 26 | "source": [ 27 | "## Step 0: Config Setting" 28 | ] 29 | }, 30 | { 31 | "cell_type": "code", 32 | "execution_count": 1, 33 | "metadata": { 34 | "id": "8kZ_1n8U85GQ" 35 | }, 36 | "outputs": [], 37 | "source": [ 38 | "# 如果你想要在 Google Colab 長期測試，你可以使用 ngrok 來做服務器代理的處理\n", 39 | "# 到官方網站註冊帳號：https://ngrok.com/\n", 40 | "# 申請token，你就可以將以下變數進行更換。\n", 41 | "NGROK_TOKEN = None" 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": 2, 47 | "metadata": { 48 | "id": "Vru9EFFb9lmp" 49 | }, 50 | "outputs": [], 51 | "source": [ 52 | "# GGUF Model\n", 53 | "# 你可以到 HuggingFace 去找尋相關的 GGUF 模型\n", 54 | "# Example:\n", 55 | "# Llama: https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF\n", 56 | "# Taiwan Llama: https://huggingface.co/audreyt/Taiwan-LLaMa-v1.0-GGUF\n", 57 | "GGUF_HUGGINGFACE_REPO = \"TheBloke/Mistral-7B-Instruct-v0.1-GGUF\"\n", 58 | "GGUF_HUGGINGFACE_BIN_FILE = \"mistral-7b-instruct-v0.1.Q5_0.gguf\"" 59 | ] 60 | }, 61 | { 62 | "cell_type": "markdown", 63 | "metadata": { 64 | "id": "BXt_MjHG9Fw-" 65 | }, 66 | "source": [ 67 | "## Step 1: Install python package" 68 | ] 69 | }, 70 | { 71 | "cell_type": "code", 72 | "execution_count": 3, 73 | "metadata": { 74 | "colab": { 75 | "base_uri": "https://localhost:8080/" 76 | }, 77 | "id": "iV9rhIbg6K9d", 78 | "outputId": "1bbb1a7c-490e-4762-c7a0-12f09f7a441d" 79 | }, 80 | "outputs": [ 81 | { 82 | "output_type": "stream", 83 | "name": "stdout", 84 | "text": [ 85 | "Requirement already satisfied: fastapi in /usr/local/lib/python3.10/dist-packages (0.108.0)\n", 86 | "Requirement already satisfied: nest-asyncio in /usr/local/lib/python3.10/dist-packages (1.5.8)\n", 87 | "Requirement already satisfied: pyngrok in /usr/local/lib/python3.10/dist-packages (7.0.4)\n", 88 | "Requirement already satisfied: uvicorn in /usr/local/lib/python3.10/dist-packages (0.25.0)\n", 89 | "Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (0.25.0)\n", 90 | "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.35.2)\n", 91 | "Requirement already satisfied: pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,!=2.1.0,<3.0.0,>=1.7.4 in /usr/local/lib/python3.10/dist-packages (from fastapi) (1.10.13)\n", 92 | "Requirement already satisfied: starlette<0.33.0,>=0.29.0 in /usr/local/lib/python3.10/dist-packages (from fastapi) (0.32.0.post1)\n", 93 | "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from fastapi) (4.9.0)\n", 94 | "Requirement already satisfied: PyYAML in /usr/local/lib/python3.10/dist-packages (from pyngrok) (6.0.1)\n", 95 | "Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn) (8.1.7)\n", 96 | "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn) (0.14.0)\n", 97 | "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate) (1.26.2)\n", 98 | "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (23.2)\n", 99 | "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n", 100 | "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.1.0+cu121)\n", 101 | "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.19.4)\n", 102 | "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.4.1)\n", 103 | "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.13.1)\n", 104 | "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.6.3)\n", 105 | "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n", 106 | "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.0)\n", 107 | "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.1)\n", 108 | "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (2023.6.0)\n", 109 | "Requirement already satisfied: anyio<5,>=3.4.0 in /usr/local/lib/python3.10/dist-packages (from starlette<0.33.0,>=0.29.0->fastapi) (3.7.1)\n", 110 | "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (1.12)\n", 111 | "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.2.1)\n", 112 | "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1.2)\n", 113 | "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2.1.0)\n", 114 | "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n", 115 | "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.6)\n", 116 | "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n", 117 | "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2023.11.17)\n", 118 | "Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.4.0->starlette<0.33.0,>=0.29.0->fastapi) (1.3.0)\n", 119 | "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.4.0->starlette<0.33.0,>=0.29.0->fastapi) (1.2.0)\n", 120 | "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.3)\n", 121 | "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->accelerate) (1.3.0)\n" 122 | ] 123 | } 124 | ], 125 | "source": [ 126 | "# 安裝 fastapi, nest-asyncio, pyngrok, uvicorn, accelerate 和 transformers 套件，以支援API開發和深度學習模型的操作。\n", 127 | "!pip install fastapi nest-asyncio pyngrok uvicorn accelerate transformers" 128 | ] 129 | }, 130 | { 131 | "cell_type": "code", 132 | "execution_count": 4, 133 | "metadata": { 134 | "colab": { 135 | "base_uri": "https://localhost:8080/" 136 | }, 137 | "id": "4yK3DJgd66El", 138 | "outputId": "2898f6b6-972d-42b8-bc64-e32610cdd1ff" 139 | }, 140 | "outputs": [ 141 | { 142 | "output_type": "stream", 143 | "name": "stdout", 144 | "text": [ 145 | "Using pip 23.1.2 from /usr/local/lib/python3.10/dist-packages/pip (python 3.10)\n", 146 | "Collecting llama-cpp-python==0.2.6\n", 147 | " Downloading llama_cpp_python-0.2.6.tar.gz (1.6 MB)\n", 148 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m10.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 149 | "\u001b[?25h Running command pip subprocess to install build dependencies\n", 150 | " Using pip 23.1.2 from /usr/local/lib/python3.10/dist-packages/pip (python 3.10)\n", 151 | " Collecting scikit-build-core[pyproject]>=0.5.0\n", 152 | " Using cached scikit_build_core-0.7.0-py3-none-any.whl (136 kB)\n", 153 | " Collecting exceptiongroup (from scikit-build-core[pyproject]>=0.5.0)\n", 154 | " Using cached exceptiongroup-1.2.0-py3-none-any.whl (16 kB)\n", 155 | " Collecting packaging>=20.9 (from scikit-build-core[pyproject]>=0.5.0)\n", 156 | " Using cached packaging-23.2-py3-none-any.whl (53 kB)\n", 157 | " Collecting tomli>=1.1 (from scikit-build-core[pyproject]>=0.5.0)\n", 158 | " Using cached tomli-2.0.1-py3-none-any.whl (12 kB)\n", 159 | " Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]>=0.5.0)\n", 160 | " Using cached pathspec-0.12.1-py3-none-any.whl (31 kB)\n", 161 | " Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]>=0.5.0)\n", 162 | " Using cached pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB)\n", 163 | " Installing collected packages: tomli, pathspec, packaging, exceptiongroup, scikit-build-core, pyproject-metadata\n", 164 | " ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", 165 | " lida 0.0.10 requires kaleido, which is not installed.\n", 166 | " lida 0.0.10 requires python-multipart, which is not installed.\n", 167 | " Successfully installed exceptiongroup-1.2.0 packaging-23.2 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.7.0 tomli-2.0.1\n", 168 | " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", 169 | " Running command Getting requirements to build wheel\n", 170 | " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", 171 | " Running command pip subprocess to install backend dependencies\n", 172 | " Using pip 23.1.2 from /usr/local/lib/python3.10/dist-packages/pip (python 3.10)\n", 173 | " Collecting cmake>=3.12\n", 174 | " Using cached cmake-3.28.1-py2.py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (26.3 MB)\n", 175 | " Collecting ninja>=1.5\n", 176 | " Using cached ninja-1.11.1.1-py2.py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl (307 kB)\n", 177 | " Installing collected packages: ninja, cmake\n", 178 | " Creating /tmp/pip-build-env-77ltovlp/normal/local/bin\n", 179 | " changing mode of /tmp/pip-build-env-77ltovlp/normal/local/bin/ninja to 755\n", 180 | " changing mode of /tmp/pip-build-env-77ltovlp/normal/local/bin/cmake to 755\n", 181 | " changing mode of /tmp/pip-build-env-77ltovlp/normal/local/bin/cpack to 755\n", 182 | " changing mode of /tmp/pip-build-env-77ltovlp/normal/local/bin/ctest to 755\n", 183 | " Successfully installed cmake-3.28.1 ninja-1.11.1.1\n", 184 | " Installing backend dependencies ... \u001b[?25l\u001b[?25hdone\n", 185 | " Running command Preparing metadata (pyproject.toml)\n", 186 | " *** scikit-build-core 0.7.0 using CMake 3.28.1 (metadata_wheel)\n", 187 | " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", 188 | "Collecting typing-extensions>=4.5.0 (from llama-cpp-python==0.2.6)\n", 189 | " Downloading typing_extensions-4.9.0-py3-none-any.whl (32 kB)\n", 190 | "Collecting numpy>=1.20.0 (from llama-cpp-python==0.2.6)\n", 191 | " Downloading numpy-1.26.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.2 MB)\n", 192 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.2/18.2 MB\u001b[0m \u001b[31m70.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 193 | "\u001b[?25hCollecting diskcache>=5.6.1 (from llama-cpp-python==0.2.6)\n", 194 | " Downloading diskcache-5.6.3-py3-none-any.whl (45 kB)\n", 195 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.5/45.5 kB\u001b[0m \u001b[31m124.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 196 | "\u001b[?25hBuilding wheels for collected packages: llama-cpp-python\n", 197 | " Running command Building wheel for llama-cpp-python (pyproject.toml)\n", 198 | " *** scikit-build-core 0.7.0 using CMake 3.28.1 (wheel)\n", 199 | " *** Configuring CMake...\n", 200 | " loading initial cache file /tmp/tmp0a32c0oq/build/CMakeInit.txt\n", 201 | " -- The C compiler identification is GNU 11.4.0\n", 202 | " -- The CXX compiler identification is GNU 11.4.0\n", 203 | " -- Detecting C compiler ABI info\n", 204 | " -- Detecting C compiler ABI info - done\n", 205 | " -- Check for working C compiler: /usr/bin/cc - skipped\n", 206 | " -- Detecting C compile features\n", 207 | " -- Detecting C compile features - done\n", 208 | " -- Detecting CXX compiler ABI info\n", 209 | " -- Detecting CXX compiler ABI info - done\n", 210 | " -- Check for working CXX compiler: /usr/bin/c++ - skipped\n", 211 | " -- Detecting CXX compile features\n", 212 | " -- Detecting CXX compile features - done\n", 213 | " -- Found Git: /usr/bin/git (found version \"2.34.1\")\n", 214 | " fatal: not a git repository (or any of the parent directories): .git\n", 215 | " fatal: not a git repository (or any of the parent directories): .git\n", 216 | " CMake Warning at vendor/llama.cpp/CMakeLists.txt:125 (message):\n", 217 | " Git repository not found; to enable automatic generation of build info,\n", 218 | " make sure Git is installed and the project is a Git repository.\n", 219 | "\n", 220 | "\n", 221 | " -- Performing Test CMAKE_HAVE_LIBC_PTHREAD\n", 222 | " -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success\n", 223 | " -- Found Threads: TRUE\n", 224 | " -- Found CUDAToolkit: /usr/local/cuda/targets/x86_64-linux/include (found version \"12.2.140\")\n", 225 | " -- cuBLAS found\n", 226 | " -- The CUDA compiler identification is NVIDIA 12.2.140\n", 227 | " -- Detecting CUDA compiler ABI info\n", 228 | " -- Detecting CUDA compiler ABI info - done\n", 229 | " -- Check for working CUDA compiler: /usr/local/cuda/bin/nvcc - skipped\n", 230 | " -- Detecting CUDA compile features\n", 231 | " -- Detecting CUDA compile features - done\n", 232 | " -- Using CUDA architectures: 52;61;70\n", 233 | " -- CMAKE_SYSTEM_PROCESSOR: x86_64\n", 234 | " -- x86 detected\n", 235 | " CMake Warning (dev) at CMakeLists.txt:19 (install):\n", 236 | " Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION.\n", 237 | " This warning is for project developers. Use -Wno-dev to suppress it.\n", 238 | "\n", 239 | " CMake Warning (dev) at CMakeLists.txt:28 (install):\n", 240 | " Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION.\n", 241 | " This warning is for project developers. Use -Wno-dev to suppress it.\n", 242 | "\n", 243 | " -- Configuring done (3.0s)\n", 244 | " -- Generating done (0.0s)\n", 245 | " -- Build files have been written to: /tmp/tmp0a32c0oq/build\n", 246 | " *** Building project with Ninja...\n", 247 | " Change Dir: '/tmp/tmp0a32c0oq/build'\n", 248 | "\n", 249 | " Run Build Command(s): /tmp/pip-build-env-77ltovlp/normal/local/lib/python3.10/dist-packages/ninja/data/bin/ninja -v\n", 250 | " [1/11] /usr/bin/cc -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_USE_CUBLAS -DGGML_USE_K_QUANTS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Wno-unused-function -mf16c -mfma -mavx -mavx2 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -c /tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/ggml-alloc.c\n", 251 | " [2/11] /usr/bin/cc -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_USE_CUBLAS -DGGML_USE_K_QUANTS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Wno-unused-function -mf16c -mfma -mavx -mavx2 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/k_quants.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/k_quants.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/k_quants.c.o -c /tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/k_quants.c\n", 252 | " [3/11] /usr/bin/cc -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_USE_CUBLAS -DGGML_USE_K_QUANTS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Wno-unused-function -mf16c -mfma -mavx -mavx2 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -c /tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/ggml.c\n", 253 | " [4/11] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_USE_CUBLAS -DGGML_USE_K_QUANTS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/common/. -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -Wno-format-truncation -Wno-array-bounds -mf16c -mfma -mavx -mavx2 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -c /tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/common/common.cpp\n", 254 | " [5/11] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_USE_CUBLAS -DGGML_USE_K_QUANTS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/common/. -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -Wno-format-truncation -Wno-array-bounds -mf16c -mfma -mavx -mavx2 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -c /tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/common/console.cpp\n", 255 | " [6/11] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_USE_CUBLAS -DGGML_USE_K_QUANTS -DK_QUANTS_PER_ITERATION=2 -DLLAMA_BUILD -DLLAMA_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dllama_EXPORTS -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -Wno-format-truncation -Wno-array-bounds -mf16c -mfma -mavx -mavx2 -MD -MT vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -MF vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o.d -o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -c /tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/llama.cpp\n", 256 | " [7/11] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_USE_CUBLAS -DGGML_USE_K_QUANTS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/common/. -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -Wno-format-truncation -Wno-array-bounds -mf16c -mfma -mavx -mavx2 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -c /tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/common/grammar-parser.cpp\n", 257 | " [8/11] /usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_USE_CUBLAS -DGGML_USE_K_QUANTS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=c++11 \"--generate-code=arch=compute_52,code=[compute_52,sm_52]\" \"--generate-code=arch=compute_61,code=[compute_61,sm_61]\" \"--generate-code=arch=compute_70,code=[compute_70,sm_70]\" -Xcompiler=-fPIC -mf16c -mfma -mavx -mavx2 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o.d -x cu -c /tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/vendor/llama.cpp/ggml-cuda.cu -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o\n", 258 | " [9/11] : && /usr/bin/c++ -fPIC -O3 -DNDEBUG -shared -Wl,-soname,libllama.so -o vendor/llama.cpp/libllama.so vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o vendor/llama.cpp/CMakeFiles/ggml.dir/k_quants.c.o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -L/usr/local/cuda/targets/x86_64-linux/lib -Wl,-rpath,/usr/local/cuda-12.2/targets/x86_64-linux/lib: /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libculibos.a -lcudadevrt -lcudart_static -lrt -lpthread -ldl && :\n", 259 | " [10/11] : && /tmp/pip-build-env-77ltovlp/normal/local/lib/python3.10/dist-packages/cmake/data/bin/cmake -E rm -f vendor/llama.cpp/libggml_static.a && /usr/bin/ar qc vendor/llama.cpp/libggml_static.a vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o vendor/llama.cpp/CMakeFiles/ggml.dir/k_quants.c.o && /usr/bin/ranlib vendor/llama.cpp/libggml_static.a && :\n", 260 | " [11/11] : && /usr/bin/g++ -fPIC -shared -Wl,-soname,libggml_shared.so -o vendor/llama.cpp/libggml_shared.so vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o vendor/llama.cpp/CMakeFiles/ggml.dir/k_quants.c.o /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libculibos.a -lcudadevrt -lcudart_static -lrt -lpthread -ldl -L\"/usr/local/cuda/targets/x86_64-linux/lib/stubs\" -L\"/usr/local/cuda/targets/x86_64-linux/lib\" && :\n", 261 | "\n", 262 | " *** Installing project into wheel...\n", 263 | " -- Install configuration: \"Release\"\n", 264 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/lib/libggml_shared.so\n", 265 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake\n", 266 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake\n", 267 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/include/ggml.h\n", 268 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/include/ggml-cuda.h\n", 269 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/include/k_quants.h\n", 270 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/lib/libllama.so\n", 271 | " -- Set non-toolchain portion of runtime path of \"/tmp/tmp0a32c0oq/wheel/platlib/lib/libllama.so\" to \"\"\n", 272 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/include/llama.h\n", 273 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/bin/convert.py\n", 274 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/bin/convert-lora-to-ggml.py\n", 275 | " -- Installing: /tmp/tmp0a32c0oq/wheel/platlib/llama_cpp/libllama.so\n", 276 | " -- Set non-toolchain portion of runtime path of \"/tmp/tmp0a32c0oq/wheel/platlib/llama_cpp/libllama.so\" to \"\"\n", 277 | " -- Installing: /tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/llama_cpp/libllama.so\n", 278 | " -- Set non-toolchain portion of runtime path of \"/tmp/pip-install-dyvotvmv/llama-cpp-python_9ec4ea79d9674f8db922d78ab341a2ab/llama_cpp/libllama.so\" to \"\"\n", 279 | " *** Making wheel...\n", 280 | " *** Created llama_cpp_python-0.2.6-cp310-cp310-manylinux_2_35_x86_64.whl...\n", 281 | " Building wheel for llama-cpp-python (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", 282 | " Created wheel for llama-cpp-python: filename=llama_cpp_python-0.2.6-cp310-cp310-manylinux_2_35_x86_64.whl size=6192165 sha256=1774b011f68125ed03876b4c243e15e8a7f1dde3ee09dcaf6e6aeb4973425b48\n", 283 | " Stored in directory: /tmp/pip-ephem-wheel-cache-b_c8sr65/wheels/6c/ae/75/c2ad88ef0d1e219f981c51367b8533025345d1a14aa2f09662\n", 284 | "Successfully built llama-cpp-python\n", 285 | "Installing collected packages: typing-extensions, numpy, diskcache, llama-cpp-python\n", 286 | " Attempting uninstall: typing-extensions\n", 287 | " Found existing installation: typing_extensions 4.9.0\n", 288 | " Uninstalling typing_extensions-4.9.0:\n", 289 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/__pycache__/typing_extensions.cpython-310.pyc\n", 290 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/typing_extensions-4.9.0.dist-info/\n", 291 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/typing_extensions.py\n", 292 | " Successfully uninstalled typing_extensions-4.9.0\n", 293 | " Attempting uninstall: numpy\n", 294 | " Found existing installation: numpy 1.26.2\n", 295 | " Uninstalling numpy-1.26.2:\n", 296 | " Removing file or directory /usr/local/bin/f2py\n", 297 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/numpy-1.26.2.dist-info/\n", 298 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/numpy.libs/\n", 299 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/numpy/\n", 300 | " Successfully uninstalled numpy-1.26.2\n", 301 | " changing mode of /usr/local/bin/f2py to 755\n", 302 | " Attempting uninstall: diskcache\n", 303 | " Found existing installation: diskcache 5.6.3\n", 304 | " Uninstalling diskcache-5.6.3:\n", 305 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/diskcache-5.6.3.dist-info/\n", 306 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/diskcache/\n", 307 | " Successfully uninstalled diskcache-5.6.3\n", 308 | " Attempting uninstall: llama-cpp-python\n", 309 | " Found existing installation: llama_cpp_python 0.2.6\n", 310 | " Uninstalling llama_cpp_python-0.2.6:\n", 311 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/bin/__pycache__/convert-lora-to-ggml.cpython-310.pyc\n", 312 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/bin/__pycache__/convert.cpython-310.pyc\n", 313 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/bin/convert-lora-to-ggml.py\n", 314 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/bin/convert.py\n", 315 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/include/\n", 316 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/lib/\n", 317 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/llama_cpp/\n", 318 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/llama_cpp_python-0.2.6.dist-info/\n", 319 | " Successfully uninstalled llama_cpp_python-0.2.6\n", 320 | "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", 321 | "lida 0.0.10 requires kaleido, which is not installed.\n", 322 | "lida 0.0.10 requires python-multipart, which is not installed.\n", 323 | "llmx 0.0.15a0 requires cohere, which is not installed.\n", 324 | "llmx 0.0.15a0 requires openai, which is not installed.\n", 325 | "llmx 0.0.15a0 requires tiktoken, which is not installed.\n", 326 | "tensorflow-probability 0.22.0 requires typing-extensions<4.6.0, but you have typing-extensions 4.9.0 which is incompatible.\u001b[0m\u001b[31m\n", 327 | "\u001b[0mSuccessfully installed diskcache-5.6.3 llama-cpp-python-0.2.6 numpy-1.26.2 typing-extensions-4.9.0\n" 328 | ] 329 | } 330 | ], 331 | "source": [ 332 | "# 安裝特定版本的 llama-cpp-python 套件，並啟用 CUDA 的 cuBLAS 功能。\n", 333 | "# `--force-reinstall` 會強制重新安裝，`--upgrade` 會確保安裝最新版本，而 `--no-cache-dir` 會避免使用本地快取，`--verbose` 提供詳細的輸出。\n", 334 | "!CMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" FORCE_CMAKE=1 pip install llama-cpp-python==0.2.25 --force-reinstall --upgrade --no-cache-dir --verbose" 335 | ] 336 | }, 337 | { 338 | "cell_type": "code", 339 | "execution_count": 5, 340 | "metadata": { 341 | "colab": { 342 | "base_uri": "https://localhost:8080/" 343 | }, 344 | "id": "dRoUDXE666sk", 345 | "outputId": "c769c39a-5989-4a7e-aae3-7591639832be" 346 | }, 347 | "outputs": [ 348 | { 349 | "output_type": "stream", 350 | "name": "stdout", 351 | "text": [ 352 | "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.19.4)\n", 353 | "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (3.13.1)\n", 354 | "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2023.6.0)\n", 355 | "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2.31.0)\n", 356 | "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.66.1)\n", 357 | "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (6.0.1)\n", 358 | "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.9.0)\n", 359 | "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (23.2)\n", 360 | "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.3.2)\n", 361 | "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.6)\n", 362 | "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2.0.7)\n", 363 | "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2023.11.17)\n" 364 | ] 365 | } 366 | ], 367 | "source": [ 368 | "# 安裝 huggingface_hub 套件，此套件可支援與 Hugging Face Model Hub 進行交互。\n", 369 | "!pip install huggingface_hub" 370 | ] 371 | }, 372 | { 373 | "cell_type": "markdown", 374 | "metadata": { 375 | "id": "k7ye1-jg7x8r" 376 | }, 377 | "source": [ 378 | "## Step 2: Download GGUF Model and predict the result" 379 | ] 380 | }, 381 | { 382 | "cell_type": "code", 383 | "execution_count": 6, 384 | "metadata": { 385 | "id": "u4LMufzw6jUU" 386 | }, 387 | "outputs": [], 388 | "source": [ 389 | "import json\n", 390 | "import logging\n", 391 | "from huggingface_hub import hf_hub_download\n", 392 | "from llama_cpp import Llama\n", 393 | "\n", 394 | "# 設定日誌\n", 395 | "logging.basicConfig(level=logging.INFO,\n", 396 | " format='%(asctime)s [%(levelname)s] %(message)s',\n", 397 | " datefmt='%Y-%m-%d %H:%M:%S')\n", 398 | "logger = logging.getLogger(__name__)\n", 399 | "\n", 400 | "class Model:\n", 401 | " def __init__(self):\n", 402 | " self.loaded = False # 模型是否已經加載的標志\n", 403 | " self.lcpp_llm = None # 儲存 Llama 模型的變數\n", 404 | " self.model_path = \"\" # 模型的路徑\n", 405 | "\n", 406 | " def load(self, model_name_or_path = \"TheBloke/Llama-2-13B-chat-GGUF\", model_basename = \"llama-2-13b-chat.Q5_0.gguf\"):\n", 407 | " # 從 Hugging Face Model Hub 下載模型並設定其路徑\n", 408 | " self.model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)\n", 409 | " logger.info(\"Finish: Load Llama 2 model.\") # 輸出模型加載完成的信息\n", 410 | "\n", 411 | " def predict(self, data):\n", 412 | " # 如果模型還沒有被加載，則加載模型\n", 413 | " if not self.loaded:\n", 414 | " self.loaded = True\n", 415 | " self.lcpp_llm = Llama(\n", 416 | " model_path=self.model_path,\n", 417 | " n_threads=2, # 使用的執行緒數量\n", 418 | " n_batch=1024, # 批次大小\n", 419 | " n_gpu_layers=32 # 使用的GPU層數\n", 420 | " )\n", 421 | " logger.info(\"========== Start ==========\")\n", 422 | " # 將 JSON 字符串反序列化成字典\n", 423 | " # data_dict = json.loads(data)\n", 424 | " # logger.info(\"Input: {}.\".format(data_dict))\n", 425 | " # 使用 Llama 模型進行預測\n", 426 | " response = self.lcpp_llm.create_chat_completion(**data)\n", 427 | " # logger.info(\"Response: {}.\".format(response))\n", 428 | " logger.info(\"========== End ==========\")\n", 429 | "\n", 430 | " return response # 返回模型的預測結果" 431 | ] 432 | }, 433 | { 434 | "cell_type": "code", 435 | "execution_count": 7, 436 | "metadata": { 437 | "id": "uiHZFZGf6kSd" 438 | }, 439 | "outputs": [], 440 | "source": [ 441 | "model_instance = Model()\n", 442 | "model_instance.load(model_name_or_path = GGUF_HUGGINGFACE_REPO, model_basename = GGUF_HUGGINGFACE_BIN_FILE)" 443 | ] 444 | }, 445 | { 446 | "cell_type": "code", 447 | "source": [ 448 | "data = {\n", 449 | " \"messages\": [\n", 450 | " {\n", 451 | " \"role\": \"system\",\n", 452 | " \"content\": \"你是一個有幫助的問答機器人，請用繁體中文回覆。\"\n", 453 | " },\n", 454 | " {\n", 455 | " \"role\": \"user\",\n", 456 | " \"content\": \"台灣首都在哪裏？\"\n", 457 | " }\n", 458 | " ]\n", 459 | "}" 460 | ], 461 | "metadata": { 462 | "id": "XMAyC2ijkQgr" 463 | }, 464 | "execution_count": 8, 465 | "outputs": [] 466 | }, 467 | { 468 | "cell_type": "code", 469 | "source": [ 470 | "model_instance.predict(data)" 471 | ], 472 | "metadata": { 473 | "colab": { 474 | "base_uri": "https://localhost:8080/" 475 | }, 476 | "id": "2NSVUPVDiy81", 477 | "outputId": "2f22bdbf-e704-4670-e439-f27b87bf153a" 478 | }, 479 | "execution_count": 9, 480 | "outputs": [ 481 | { 482 | "output_type": "stream", 483 | "name": "stderr", 484 | "text": [ 485 | "AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | \n" 486 | ] 487 | }, 488 | { 489 | "output_type": "execute_result", 490 | "data": { 491 | "text/plain": [ 492 | "{'id': 'chatcmpl-bdca1b41-963b-4510-adf8-2666fe409b4c',\n", 493 | " 'object': 'chat.completion',\n", 494 | " 'created': 1703734844,\n", 495 | " 'model': '/root/.cache/huggingface/hub/models--TheBloke--Mistral-7B-Instruct-v0.1-GGUF/snapshots/731a9fc8f06f5f5e2db8a0cf9d256197eb6e05d1/mistral-7b-instruct-v0.1.Q5_0.gguf',\n", 496 | " 'choices': [{'index': 0,\n", 497 | " 'message': {'role': 'assistant', 'content': '台灣首都位於台北市中心。'},\n", 498 | " 'finish_reason': 'stop'}],\n", 499 | " 'usage': {'prompt_tokens': 45, 'completion_tokens': 12, 'total_tokens': 57}}" 500 | ] 501 | }, 502 | "metadata": {}, 503 | "execution_count": 9 504 | } 505 | ] 506 | }, 507 | { 508 | "cell_type": "markdown", 509 | "metadata": { 510 | "id": "-W4IKvhb7-E4" 511 | }, 512 | "source": [ 513 | "## Step 3: Build the fastapi service" 514 | ] 515 | }, 516 | { 517 | "cell_type": "code", 518 | "execution_count": 10, 519 | "metadata": { 520 | "id": "BoM5mJIe6kP7" 521 | }, 522 | "outputs": [], 523 | "source": [ 524 | "from fastapi import FastAPI\n", 525 | "from fastapi.middleware.cors import CORSMiddleware\n", 526 | "\n", 527 | "# 初始化 FastAPI 應用\n", 528 | "app = FastAPI()\n", 529 | "\n", 530 | "# 為 FastAPI 應用加入 CORS 中間件，允許跨域請求\n", 531 | "app.add_middleware(\n", 532 | " CORSMiddleware,\n", 533 | " allow_origins=['*'], # 允許所有來源的跨域請求\n", 534 | " allow_credentials=True, # 允許憑證（例如 cookies、HTTP認證）的傳遞\n", 535 | " allow_methods=['*'], # 允許所有的 HTTP 方法\n", 536 | " allow_headers=['*'], # 允許所有的 HTTP 頭部\n", 537 | ")\n", 538 | "\n", 539 | "@app.post(\"/predict\") # 定義一個 POST 路由，用於模型預測\n", 540 | "async def predict_text(json_input: dict): # 接收一個字典格式的 JSON 輸入\n", 541 | " result = model_instance.predict(json_input) # 使用模型實例進行預測\n", 542 | " return result # 返回預測結果\n" 543 | ] 544 | }, 545 | { 546 | "cell_type": "markdown", 547 | "metadata": { 548 | "id": "bQ7WeIyg8C73" 549 | }, 550 | "source": [ 551 | "## Step 4: Start the fastapi service" 552 | ] 553 | }, 554 | { 555 | "cell_type": "code", 556 | "execution_count": 11, 557 | "metadata": { 558 | "colab": { 559 | "base_uri": "https://localhost:8080/" 560 | }, 561 | "id": "sMC363JK82jq", 562 | "outputId": "5d23fe8c-77ac-4131-e824-48075f10eedb" 563 | }, 564 | "outputs": [ 565 | { 566 | "output_type": "stream", 567 | "name": "stderr", 568 | "text": [ 569 | "INFO: Started server process [4371]\n", 570 | "INFO: Waiting for application startup.\n", 571 | "INFO: Application startup complete.\n", 572 | "INFO: Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)\n" 573 | ] 574 | }, 575 | { 576 | "output_type": "stream", 577 | "name": "stdout", 578 | "text": [ 579 | "Public URL: https://d415-35-237-125-93.ngrok-free.app\n", 580 | "You can use https://d415-35-237-125-93.ngrok-free.app/predict to get the assistant result.\n" 581 | ] 582 | }, 583 | { 584 | "output_type": "stream", 585 | "name": "stderr", 586 | "text": [ 587 | "WARNING:pyngrok.process.ngrok:t=2023-12-28T03:41:06+0000 lvl=warn msg=\"Stopping forwarder\" name=http-8000-bbf6b256-55b9-40e3-a412-dce1a5e0ded2 acceptErr=\"failed to accept connection: Listener closed\"\n", 588 | "INFO: Shutting down\n", 589 | "INFO: Waiting for application shutdown.\n", 590 | "INFO: Application shutdown complete.\n", 591 | "INFO: Finished server process [4371]\n" 592 | ] 593 | } 594 | ], 595 | "source": [ 596 | "import nest_asyncio\n", 597 | "from pyngrok import ngrok\n", 598 | "import uvicorn\n", 599 | "\n", 600 | "# 設定 ngrok 的授權令牌\n", 601 | "if NGROK_TOKEN is not None:\n", 602 | " ngrok.set_auth_token(NGROK_TOKEN)\n", 603 | "\n", 604 | "# 建立與 ngrok 的隧道，使外部可以訪問本地的 8000 端口\n", 605 | "ngrok_tunnel = ngrok.connect(8000)\n", 606 | "public_url = ngrok_tunnel.public_url\n", 607 | "\n", 608 | "print('Public URL:', public_url) # 輸出公開的 URL\n", 609 | "print(\"You can use {}/predict to get the assistant result.\".format(public_url))\n", 610 | "\n", 611 | "\n", 612 | "# 使用 nest_asyncio 修正異步事件循環的問題\n", 613 | "nest_asyncio.apply()\n", 614 | "\n", 615 | "# 啟動 uvicorn 伺服器，使 FastAPI 應用運行在 8000 端口\n", 616 | "uvicorn.run(app, port=8000)\n" 617 | ] 618 | }, 619 | { 620 | "cell_type": "markdown", 621 | "metadata": { 622 | "id": "PuWit7ePf2om" 623 | }, 624 | "source": [ 625 | "### Example CURL command line:\n", 626 | "\n", 627 | "```bash\n", 628 | "curl --location 'https://f1b8-35-184-42-82.ngrok-free.app/predict' \\\n", 629 | "--header 'Content-Type: application/json' \\\n", 630 | "--data '{\"prompt\": \"test\", \"max_tokens\": 2}'\n", 631 | "```" 632 | ] 633 | } 634 | ], 635 | "metadata": { 636 | "accelerator": "GPU", 637 | "colab": { 638 | "gpuType": "T4", 639 | "provenance": [] 640 | }, 641 | "kernelspec": { 642 | "display_name": "Python 3", 643 | "name": "python3" 644 | }, 645 | "language_info": { 646 | "name": "python" 647 | } 648 | }, 649 | "nbformat": 4, 650 | "nbformat_minor": 0 651 | } -------------------------------------------------------------------------------- /Llama_2_FastAPI_Service_Colab_Example.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": { 6 | "id": "VUC9Opfd8Mpt" 7 | }, 8 | "source": [ 9 | "# Llama 2 Fastapi Service Example" 10 | ] 11 | }, 12 | { 13 | "cell_type": "markdown", 14 | "metadata": { 15 | "id": "e9e9QOWD-l7k" 16 | }, 17 | "source": [ 18 | "推薦至少使用 T4 GPU 來作為你的服務啟用" 19 | ] 20 | }, 21 | { 22 | "cell_type": "markdown", 23 | "metadata": { 24 | "id": "h4zPTxsL7rUn" 25 | }, 26 | "source": [ 27 | "## Step 0: Config Setting" 28 | ] 29 | }, 30 | { 31 | "cell_type": "code", 32 | "execution_count": 1, 33 | "metadata": { 34 | "id": "8kZ_1n8U85GQ" 35 | }, 36 | "outputs": [], 37 | "source": [ 38 | "# 如果你想要在 Google Colab 長期測試，你可以使用 ngrok 來做服務器代理的處理\n", 39 | "# 到官方網站註冊帳號：https://ngrok.com/\n", 40 | "# 申請token，你就可以將以下變數進行更換。\n", 41 | "NGROK_TOKEN = None" 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": 2, 47 | "metadata": { 48 | "id": "Vru9EFFb9lmp" 49 | }, 50 | "outputs": [], 51 | "source": [ 52 | "# GGML Model\n", 53 | "# 你可以到 HuggingFace 去找尋相關的 GGML 模型\n", 54 | "# Example:\n", 55 | "# Llama: https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML\n", 56 | "# Taiwan Llama: https://huggingface.co/audreyt/Taiwan-LLaMa-v1.0-GGML\n", 57 | "GGML_HUGGINGFACE_REPO = \"audreyt/Taiwan-LLaMa-v1.0-GGML\"\n", 58 | "GGML_HUGGINGFACE_BIN_FILE = \"Taiwan-LLaMa-13b-1.0.ggmlv3.q5_1.bin\"" 59 | ] 60 | }, 61 | { 62 | "cell_type": "markdown", 63 | "metadata": { 64 | "id": "BXt_MjHG9Fw-" 65 | }, 66 | "source": [ 67 | "## Step 1: Install python package" 68 | ] 69 | }, 70 | { 71 | "cell_type": "code", 72 | "execution_count": 3, 73 | "metadata": { 74 | "colab": { 75 | "base_uri": "https://localhost:8080/" 76 | }, 77 | "id": "iV9rhIbg6K9d", 78 | "outputId": "14ed91c8-cc60-4ee4-b0a9-191d9a3a762f" 79 | }, 80 | "outputs": [ 81 | { 82 | "name": "stdout", 83 | "output_type": "stream", 84 | "text": [ 85 | "Requirement already satisfied: fastapi in /usr/local/lib/python3.10/dist-packages (0.103.1)\n", 86 | "Requirement already satisfied: nest-asyncio in /usr/local/lib/python3.10/dist-packages (1.5.7)\n", 87 | "Requirement already satisfied: pyngrok in /usr/local/lib/python3.10/dist-packages (6.0.0)\n", 88 | "Requirement already satisfied: uvicorn in /usr/local/lib/python3.10/dist-packages (0.23.2)\n", 89 | "Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (0.22.0)\n", 90 | "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.33.1)\n", 91 | "Requirement already satisfied: anyio<4.0.0,>=3.7.1 in /usr/local/lib/python3.10/dist-packages (from fastapi) (3.7.1)\n", 92 | "Requirement already satisfied: pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,!=2.1.0,<3.0.0,>=1.7.4 in /usr/local/lib/python3.10/dist-packages (from fastapi) (1.10.12)\n", 93 | "Requirement already satisfied: starlette<0.28.0,>=0.27.0 in /usr/local/lib/python3.10/dist-packages (from fastapi) (0.27.0)\n", 94 | "Requirement already satisfied: typing-extensions>=4.5.0 in /usr/local/lib/python3.10/dist-packages (from fastapi) (4.7.1)\n", 95 | "Requirement already satisfied: PyYAML in /usr/local/lib/python3.10/dist-packages (from pyngrok) (6.0.1)\n", 96 | "Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn) (8.1.7)\n", 97 | "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn) (0.14.0)\n", 98 | "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate) (1.25.2)\n", 99 | "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (23.1)\n", 100 | "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n", 101 | "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.0.1+cu118)\n", 102 | "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.12.2)\n", 103 | "Requirement already satisfied: huggingface-hub<1.0,>=0.15.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.16.4)\n", 104 | "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.6.3)\n", 105 | "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n", 106 | "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.13.3)\n", 107 | "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.3.3)\n", 108 | "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.1)\n", 109 | "Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<4.0.0,>=3.7.1->fastapi) (3.4)\n", 110 | "Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<4.0.0,>=3.7.1->fastapi) (1.3.0)\n", 111 | "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<4.0.0,>=3.7.1->fastapi) (1.1.3)\n", 112 | "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.15.1->transformers) (2023.6.0)\n", 113 | "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (1.12)\n", 114 | "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1)\n", 115 | "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1.2)\n", 116 | "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2.0.0)\n", 117 | "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.10.0->accelerate) (3.27.4.1)\n", 118 | "Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.10.0->accelerate) (16.0.6)\n", 119 | "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.2.0)\n", 120 | "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.4)\n", 121 | "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2023.7.22)\n", 122 | "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.3)\n", 123 | "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->accelerate) (1.3.0)\n" 124 | ] 125 | } 126 | ], 127 | "source": [ 128 | "# 安裝 fastapi, nest-asyncio, pyngrok, uvicorn, accelerate 和 transformers 套件，以支援API開發和深度學習模型的操作。\n", 129 | "!pip install fastapi nest-asyncio pyngrok uvicorn accelerate transformers" 130 | ] 131 | }, 132 | { 133 | "cell_type": "code", 134 | "execution_count": 4, 135 | "metadata": { 136 | "colab": { 137 | "base_uri": "https://localhost:8080/" 138 | }, 139 | "id": "4yK3DJgd66El", 140 | "outputId": "02dc946a-23cb-49fa-dacd-067e21499b32" 141 | }, 142 | "outputs": [ 143 | { 144 | "name": "stdout", 145 | "output_type": "stream", 146 | "text": [ 147 | "Using pip 23.1.2 from /usr/local/lib/python3.10/dist-packages/pip (python 3.10)\n", 148 | "Collecting llama-cpp-python==0.1.77\n", 149 | " Downloading llama_cpp_python-0.1.77.tar.gz (1.6 MB)\n", 150 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m11.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 151 | "\u001b[?25h Running command pip subprocess to install build dependencies\n", 152 | " Using pip 23.1.2 from /usr/local/lib/python3.10/dist-packages/pip (python 3.10)\n", 153 | " Collecting setuptools>=42\n", 154 | " Using cached setuptools-68.2.0-py3-none-any.whl (807 kB)\n", 155 | " Collecting scikit-build>=0.13\n", 156 | " Using cached scikit_build-0.17.6-py3-none-any.whl (84 kB)\n", 157 | " Collecting cmake>=3.18\n", 158 | " Using cached cmake-3.27.4.1-py2.py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (26.1 MB)\n", 159 | " Collecting ninja\n", 160 | " Using cached ninja-1.11.1-py2.py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (145 kB)\n", 161 | " Collecting distro (from scikit-build>=0.13)\n", 162 | " Using cached distro-1.8.0-py3-none-any.whl (20 kB)\n", 163 | " Collecting packaging (from scikit-build>=0.13)\n", 164 | " Using cached packaging-23.1-py3-none-any.whl (48 kB)\n", 165 | " Collecting tomli (from scikit-build>=0.13)\n", 166 | " Using cached tomli-2.0.1-py3-none-any.whl (12 kB)\n", 167 | " Collecting wheel>=0.32.0 (from scikit-build>=0.13)\n", 168 | " Using cached wheel-0.41.2-py3-none-any.whl (64 kB)\n", 169 | " Installing collected packages: ninja, cmake, wheel, tomli, setuptools, packaging, distro, scikit-build\n", 170 | " Creating /tmp/pip-build-env-48s4me10/overlay/local/bin\n", 171 | " changing mode of /tmp/pip-build-env-48s4me10/overlay/local/bin/ninja to 755\n", 172 | " changing mode of /tmp/pip-build-env-48s4me10/overlay/local/bin/cmake to 755\n", 173 | " changing mode of /tmp/pip-build-env-48s4me10/overlay/local/bin/cpack to 755\n", 174 | " changing mode of /tmp/pip-build-env-48s4me10/overlay/local/bin/ctest to 755\n", 175 | " changing mode of /tmp/pip-build-env-48s4me10/overlay/local/bin/wheel to 755\n", 176 | " changing mode of /tmp/pip-build-env-48s4me10/overlay/local/bin/distro to 755\n", 177 | " ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", 178 | " ipython 7.34.0 requires jedi>=0.16, which is not installed.\n", 179 | " numba 0.56.4 requires numpy<1.24,>=1.18, but you have numpy 1.25.2 which is incompatible.\n", 180 | " tensorflow 2.13.0 requires numpy<=1.24.3,>=1.22, but you have numpy 1.25.2 which is incompatible.\n", 181 | " tensorflow 2.13.0 requires typing-extensions<4.6.0,>=3.6.6, but you have typing-extensions 4.7.1 which is incompatible.\n", 182 | " Successfully installed cmake-3.27.4.1 distro-1.8.0 ninja-1.11.1 packaging-23.1 scikit-build-0.17.6 setuptools-68.2.0 tomli-2.0.1 wheel-0.41.2\n", 183 | " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", 184 | " Running command Getting requirements to build wheel\n", 185 | " running egg_info\n", 186 | " writing llama_cpp_python.egg-info/PKG-INFO\n", 187 | " writing dependency_links to llama_cpp_python.egg-info/dependency_links.txt\n", 188 | " writing requirements to llama_cpp_python.egg-info/requires.txt\n", 189 | " writing top-level names to llama_cpp_python.egg-info/top_level.txt\n", 190 | " reading manifest file 'llama_cpp_python.egg-info/SOURCES.txt'\n", 191 | " adding license file 'LICENSE.md'\n", 192 | " writing manifest file 'llama_cpp_python.egg-info/SOURCES.txt'\n", 193 | " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", 194 | " Running command Preparing metadata (pyproject.toml)\n", 195 | " running dist_info\n", 196 | " creating /tmp/pip-modern-metadata-qm_wd844/llama_cpp_python.egg-info\n", 197 | " writing /tmp/pip-modern-metadata-qm_wd844/llama_cpp_python.egg-info/PKG-INFO\n", 198 | " writing dependency_links to /tmp/pip-modern-metadata-qm_wd844/llama_cpp_python.egg-info/dependency_links.txt\n", 199 | " writing requirements to /tmp/pip-modern-metadata-qm_wd844/llama_cpp_python.egg-info/requires.txt\n", 200 | " writing top-level names to /tmp/pip-modern-metadata-qm_wd844/llama_cpp_python.egg-info/top_level.txt\n", 201 | " writing manifest file '/tmp/pip-modern-metadata-qm_wd844/llama_cpp_python.egg-info/SOURCES.txt'\n", 202 | " reading manifest file '/tmp/pip-modern-metadata-qm_wd844/llama_cpp_python.egg-info/SOURCES.txt'\n", 203 | " adding license file 'LICENSE.md'\n", 204 | " writing manifest file '/tmp/pip-modern-metadata-qm_wd844/llama_cpp_python.egg-info/SOURCES.txt'\n", 205 | " creating '/tmp/pip-modern-metadata-qm_wd844/llama_cpp_python-0.1.77.dist-info'\n", 206 | " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", 207 | "Collecting typing-extensions>=4.5.0 (from llama-cpp-python==0.1.77)\n", 208 | " Downloading typing_extensions-4.7.1-py3-none-any.whl (33 kB)\n", 209 | "Collecting numpy>=1.20.0 (from llama-cpp-python==0.1.77)\n", 210 | " Downloading numpy-1.25.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.2 MB)\n", 211 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.2/18.2 MB\u001b[0m \u001b[31m70.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 212 | "\u001b[?25hCollecting diskcache>=5.6.1 (from llama-cpp-python==0.1.77)\n", 213 | " Downloading diskcache-5.6.3-py3-none-any.whl (45 kB)\n", 214 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.5/45.5 kB\u001b[0m \u001b[31m173.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 215 | "\u001b[?25hBuilding wheels for collected packages: llama-cpp-python\n", 216 | " Running command Building wheel for llama-cpp-python (pyproject.toml)\n", 217 | "\n", 218 | "\n", 219 | " --------------------------------------------------------------------------------\n", 220 | " -- Trying 'Ninja' generator\n", 221 | " --------------------------------\n", 222 | " ---------------------------\n", 223 | " ----------------------\n", 224 | " -----------------\n", 225 | " ------------\n", 226 | " -------\n", 227 | " --\n", 228 | " CMake Deprecation Warning at CMakeLists.txt:1 (cmake_minimum_required):\n", 229 | " Compatibility with CMake < 3.5 will be removed from a future version of\n", 230 | " CMake.\n", 231 | "\n", 232 | " Update the VERSION argument value or use a ... suffix to tell\n", 233 | " CMake that the project does not need compatibility with older versions.\n", 234 | "\n", 235 | " Not searching for unused variables given on the command line.\n", 236 | "\n", 237 | " -- The C compiler identification is GNU 11.4.0\n", 238 | " -- Detecting C compiler ABI info\n", 239 | " -- Detecting C compiler ABI info - done\n", 240 | " -- Check for working C compiler: /usr/bin/cc - skipped\n", 241 | " -- Detecting C compile features\n", 242 | " -- Detecting C compile features - done\n", 243 | " -- The CXX compiler identification is GNU 11.4.0\n", 244 | " -- Detecting CXX compiler ABI info\n", 245 | " -- Detecting CXX compiler ABI info - done\n", 246 | " -- Check for working CXX compiler: /usr/bin/c++ - skipped\n", 247 | " -- Detecting CXX compile features\n", 248 | " -- Detecting CXX compile features - done\n", 249 | " -- Configuring done (0.9s)\n", 250 | " -- Generating done (0.0s)\n", 251 | " -- Build files have been written to: /tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_cmake_test_compile/build\n", 252 | " --\n", 253 | " -------\n", 254 | " ------------\n", 255 | " -----------------\n", 256 | " ----------------------\n", 257 | " ---------------------------\n", 258 | " --------------------------------\n", 259 | " -- Trying 'Ninja' generator - success\n", 260 | " --------------------------------------------------------------------------------\n", 261 | "\n", 262 | " Configuring Project\n", 263 | " Working directory:\n", 264 | " /tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_skbuild/linux-x86_64-3.10/cmake-build\n", 265 | " Command:\n", 266 | " /tmp/pip-build-env-48s4me10/overlay/local/lib/python3.10/dist-packages/cmake/data/bin/cmake /tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682 -G Ninja -DCMAKE_MAKE_PROGRAM:FILEPATH=/tmp/pip-build-env-48s4me10/overlay/local/lib/python3.10/dist-packages/ninja/data/bin/ninja --no-warn-unused-cli -DCMAKE_INSTALL_PREFIX:PATH=/tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_skbuild/linux-x86_64-3.10/cmake-install -DPYTHON_VERSION_STRING:STRING=3.10.12 -DSKBUILD:INTERNAL=TRUE -DCMAKE_MODULE_PATH:PATH=/tmp/pip-build-env-48s4me10/overlay/local/lib/python3.10/dist-packages/skbuild/resources/cmake -DPYTHON_EXECUTABLE:PATH=/usr/bin/python3 -DPYTHON_INCLUDE_DIR:PATH=/usr/include/python3.10 -DPYTHON_LIBRARY:PATH=/usr/lib/x86_64-linux-gnu/libpython3.10.so -DPython_EXECUTABLE:PATH=/usr/bin/python3 -DPython_ROOT_DIR:PATH=/usr -DPython_FIND_REGISTRY:STRING=NEVER -DPython_INCLUDE_DIR:PATH=/usr/include/python3.10 -DPython3_EXECUTABLE:PATH=/usr/bin/python3 -DPython3_ROOT_DIR:PATH=/usr -DPython3_FIND_REGISTRY:STRING=NEVER -DPython3_INCLUDE_DIR:PATH=/usr/include/python3.10 -DCMAKE_MAKE_PROGRAM:FILEPATH=/tmp/pip-build-env-48s4me10/overlay/local/lib/python3.10/dist-packages/ninja/data/bin/ninja -DLLAMA_CUBLAS=on -DCMAKE_BUILD_TYPE:STRING=Release -DLLAMA_CUBLAS=on\n", 267 | "\n", 268 | " Not searching for unused variables given on the command line.\n", 269 | " -- The C compiler identification is GNU 11.4.0\n", 270 | " -- The CXX compiler identification is GNU 11.4.0\n", 271 | " -- Detecting C compiler ABI info\n", 272 | " -- Detecting C compiler ABI info - done\n", 273 | " -- Check for working C compiler: /usr/bin/cc - skipped\n", 274 | " -- Detecting C compile features\n", 275 | " -- Detecting C compile features - done\n", 276 | " -- Detecting CXX compiler ABI info\n", 277 | " -- Detecting CXX compiler ABI info - done\n", 278 | " -- Check for working CXX compiler: /usr/bin/c++ - skipped\n", 279 | " -- Detecting CXX compile features\n", 280 | " -- Detecting CXX compile features - done\n", 281 | " -- Found Git: /usr/bin/git (found version \"2.34.1\")\n", 282 | " fatal: not a git repository (or any of the parent directories): .git\n", 283 | " fatal: not a git repository (or any of the parent directories): .git\n", 284 | " CMake Warning at vendor/llama.cpp/CMakeLists.txt:116 (message):\n", 285 | " Git repository not found; to enable automatic generation of build info,\n", 286 | " make sure Git is installed and the project is a Git repository.\n", 287 | "\n", 288 | "\n", 289 | " -- Performing Test CMAKE_HAVE_LIBC_PTHREAD\n", 290 | " -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success\n", 291 | " -- Found Threads: TRUE\n", 292 | " -- Found CUDAToolkit: /usr/local/cuda/include (found version \"11.8.89\")\n", 293 | " -- cuBLAS found\n", 294 | " -- The CUDA compiler identification is NVIDIA 11.8.89\n", 295 | " -- Detecting CUDA compiler ABI info\n", 296 | " -- Detecting CUDA compiler ABI info - done\n", 297 | " -- Check for working CUDA compiler: /usr/local/cuda/bin/nvcc - skipped\n", 298 | " -- Detecting CUDA compile features\n", 299 | " -- Detecting CUDA compile features - done\n", 300 | " -- Using CUDA architectures: 52;61\n", 301 | " -- CMAKE_SYSTEM_PROCESSOR: x86_64\n", 302 | " -- x86 detected\n", 303 | " -- Configuring done (4.3s)\n", 304 | " -- Generating done (0.0s)\n", 305 | " -- Build files have been written to: /tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_skbuild/linux-x86_64-3.10/cmake-build\n", 306 | " [1/8] Building C object vendor/llama.cpp/CMakeFiles/ggml.dir/k_quants.c.o\n", 307 | " [2/8] Building CUDA object vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o\n", 308 | " [3/8] Building C object vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o\n", 309 | " [4/8] Linking CUDA shared library vendor/llama.cpp/libggml_shared.so\n", 310 | " [5/8] Linking CUDA static library vendor/llama.cpp/libggml_static.a\n", 311 | " [6/8] Building CXX object vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o\n", 312 | " [7/8] Linking CXX shared library vendor/llama.cpp/libllama.so\n", 313 | " [7/8] Install the project...\n", 314 | " -- Install configuration: \"Release\"\n", 315 | " -- Installing: /tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_skbuild/linux-x86_64-3.10/cmake-install/lib/libggml_shared.so\n", 316 | " -- Installing: /tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_skbuild/linux-x86_64-3.10/cmake-install/lib/libllama.so\n", 317 | " -- Set runtime path of \"/tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_skbuild/linux-x86_64-3.10/cmake-install/lib/libllama.so\" to \"\"\n", 318 | " -- Installing: /tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_skbuild/linux-x86_64-3.10/cmake-install/bin/convert.py\n", 319 | " -- Installing: /tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_skbuild/linux-x86_64-3.10/cmake-install/bin/convert-lora-to-ggml.py\n", 320 | " -- Installing: /tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/libllama.so\n", 321 | " -- Set runtime path of \"/tmp/pip-install-7e36n2_7/llama-cpp-python_cb12d93090b04ba89682ace3a2944682/_skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/libllama.so\" to \"\"\n", 322 | "\n", 323 | " copying llama_cpp/llama_types.py -> _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/llama_types.py\n", 324 | " copying llama_cpp/llama.py -> _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/llama.py\n", 325 | " copying llama_cpp/llama_cpp.py -> _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/llama_cpp.py\n", 326 | " copying llama_cpp/__init__.py -> _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/__init__.py\n", 327 | " creating directory _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/server\n", 328 | " copying llama_cpp/server/__main__.py -> _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/server/__main__.py\n", 329 | " copying llama_cpp/server/app.py -> _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/server/app.py\n", 330 | " copying llama_cpp/server/__init__.py -> _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/server/__init__.py\n", 331 | "\n", 332 | " running bdist_wheel\n", 333 | " running build\n", 334 | " running build_py\n", 335 | " creating _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310\n", 336 | " creating _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp\n", 337 | " copying _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/llama_types.py -> _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp\n", 338 | " copying _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/llama.py -> _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp\n", 339 | " copying _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/llama_cpp.py -> _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp\n", 340 | " copying _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/__init__.py -> _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp\n", 341 | " creating _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/server\n", 342 | " copying _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/server/__main__.py -> _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/server\n", 343 | " copying _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/server/app.py -> _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/server\n", 344 | " copying _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/server/__init__.py -> _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/server\n", 345 | " copying _skbuild/linux-x86_64-3.10/cmake-install/llama_cpp/libllama.so -> _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp\n", 346 | " copied 7 files\n", 347 | " running build_ext\n", 348 | " installing to _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel\n", 349 | " running install\n", 350 | " running install_lib\n", 351 | " creating _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64\n", 352 | " creating _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel\n", 353 | " creating _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp\n", 354 | " copying _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/libllama.so -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp\n", 355 | " copying _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/llama_types.py -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp\n", 356 | " creating _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp/server\n", 357 | " copying _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/server/__main__.py -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp/server\n", 358 | " copying _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/server/app.py -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp/server\n", 359 | " copying _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/server/__init__.py -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp/server\n", 360 | " copying _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/llama.py -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp\n", 361 | " copying _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/llama_cpp.py -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp\n", 362 | " copying _skbuild/linux-x86_64-3.10/setuptools/lib.linux-x86_64-cpython-310/llama_cpp/__init__.py -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp\n", 363 | " copied 8 files\n", 364 | " running install_data\n", 365 | " creating _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp_python-0.1.77.data\n", 366 | " creating _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp_python-0.1.77.data/data\n", 367 | " creating _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp_python-0.1.77.data/data/lib\n", 368 | " copying _skbuild/linux-x86_64-3.10/cmake-install/lib/libllama.so -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp_python-0.1.77.data/data/lib\n", 369 | " copying _skbuild/linux-x86_64-3.10/cmake-install/lib/libggml_shared.so -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp_python-0.1.77.data/data/lib\n", 370 | " creating _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp_python-0.1.77.data/data/bin\n", 371 | " copying _skbuild/linux-x86_64-3.10/cmake-install/bin/convert.py -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp_python-0.1.77.data/data/bin\n", 372 | " copying _skbuild/linux-x86_64-3.10/cmake-install/bin/convert-lora-to-ggml.py -> _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp_python-0.1.77.data/data/bin\n", 373 | " running install_egg_info\n", 374 | " running egg_info\n", 375 | " writing llama_cpp_python.egg-info/PKG-INFO\n", 376 | " writing dependency_links to llama_cpp_python.egg-info/dependency_links.txt\n", 377 | " writing requirements to llama_cpp_python.egg-info/requires.txt\n", 378 | " writing top-level names to llama_cpp_python.egg-info/top_level.txt\n", 379 | " reading manifest file 'llama_cpp_python.egg-info/SOURCES.txt'\n", 380 | " adding license file 'LICENSE.md'\n", 381 | " writing manifest file 'llama_cpp_python.egg-info/SOURCES.txt'\n", 382 | " Copying llama_cpp_python.egg-info to _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp_python-0.1.77-py3.10.egg-info\n", 383 | " running install_scripts\n", 384 | " copied 0 files\n", 385 | " creating _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel/llama_cpp_python-0.1.77.dist-info/WHEEL\n", 386 | " creating '/tmp/pip-wheel-fu7bsbze/.tmp-vfrdieph/llama_cpp_python-0.1.77-cp310-cp310-linux_x86_64.whl' and adding '_skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel' to it\n", 387 | " adding 'llama_cpp/__init__.py'\n", 388 | " adding 'llama_cpp/libllama.so'\n", 389 | " adding 'llama_cpp/llama.py'\n", 390 | " adding 'llama_cpp/llama_cpp.py'\n", 391 | " adding 'llama_cpp/llama_types.py'\n", 392 | " adding 'llama_cpp/server/__init__.py'\n", 393 | " adding 'llama_cpp/server/__main__.py'\n", 394 | " adding 'llama_cpp/server/app.py'\n", 395 | " adding 'llama_cpp_python-0.1.77.data/data/bin/convert-lora-to-ggml.py'\n", 396 | " adding 'llama_cpp_python-0.1.77.data/data/bin/convert.py'\n", 397 | " adding 'llama_cpp_python-0.1.77.data/data/lib/libggml_shared.so'\n", 398 | " adding 'llama_cpp_python-0.1.77.data/data/lib/libllama.so'\n", 399 | " adding 'llama_cpp_python-0.1.77.dist-info/LICENSE.md'\n", 400 | " adding 'llama_cpp_python-0.1.77.dist-info/METADATA'\n", 401 | " adding 'llama_cpp_python-0.1.77.dist-info/WHEEL'\n", 402 | " adding 'llama_cpp_python-0.1.77.dist-info/top_level.txt'\n", 403 | " adding 'llama_cpp_python-0.1.77.dist-info/RECORD'\n", 404 | " removing _skbuild/linux-x86_64-3.10/setuptools/bdist.linux-x86_64/wheel\n", 405 | " Building wheel for llama-cpp-python (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", 406 | " Created wheel for llama-cpp-python: filename=llama_cpp_python-0.1.77-cp310-cp310-linux_x86_64.whl size=1368844 sha256=47ac034b15811c29178985ef36f54386cc9292d179dec7ad6bb4787e069b790d\n", 407 | " Stored in directory: /tmp/pip-ephem-wheel-cache-nuedusa9/wheels/aa/ed/39/87f2ad350dbbf13b600ac744899186b8647c5323c62e2bb348\n", 408 | "Successfully built llama-cpp-python\n", 409 | "Installing collected packages: typing-extensions, numpy, diskcache, llama-cpp-python\n", 410 | " Attempting uninstall: typing-extensions\n", 411 | " Found existing installation: typing_extensions 4.7.1\n", 412 | " Uninstalling typing_extensions-4.7.1:\n", 413 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/__pycache__/typing_extensions.cpython-310.pyc\n", 414 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/typing_extensions-4.7.1.dist-info/\n", 415 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/typing_extensions.py\n", 416 | " Successfully uninstalled typing_extensions-4.7.1\n", 417 | " Attempting uninstall: numpy\n", 418 | " Found existing installation: numpy 1.25.2\n", 419 | " Uninstalling numpy-1.25.2:\n", 420 | " Removing file or directory /usr/local/bin/f2py\n", 421 | " Removing file or directory /usr/local/bin/f2py3\n", 422 | " Removing file or directory /usr/local/bin/f2py3.10\n", 423 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/numpy-1.25.2.dist-info/\n", 424 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/numpy.libs/\n", 425 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/numpy/\n", 426 | " Successfully uninstalled numpy-1.25.2\n", 427 | " changing mode of /usr/local/bin/f2py to 755\n", 428 | " changing mode of /usr/local/bin/f2py3 to 755\n", 429 | " changing mode of /usr/local/bin/f2py3.10 to 755\n", 430 | " Attempting uninstall: diskcache\n", 431 | " Found existing installation: diskcache 5.6.3\n", 432 | " Uninstalling diskcache-5.6.3:\n", 433 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/diskcache-5.6.3.dist-info/\n", 434 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/diskcache/\n", 435 | " Successfully uninstalled diskcache-5.6.3\n", 436 | " Attempting uninstall: llama-cpp-python\n", 437 | " Found existing installation: llama-cpp-python 0.1.77\n", 438 | " Uninstalling llama-cpp-python-0.1.77:\n", 439 | " Removing file or directory /usr/local/bin/__pycache__/convert-lora-to-ggml.cpython-310.pyc\n", 440 | " Removing file or directory /usr/local/bin/__pycache__/convert.cpython-310.pyc\n", 441 | " Removing file or directory /usr/local/bin/convert-lora-to-ggml.py\n", 442 | " Removing file or directory /usr/local/bin/convert.py\n", 443 | " Removing file or directory /usr/local/lib/libggml_shared.so\n", 444 | " Removing file or directory /usr/local/lib/libllama.so\n", 445 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/llama_cpp/\n", 446 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/llama_cpp_python-0.1.77.dist-info/\n", 447 | " Successfully uninstalled llama-cpp-python-0.1.77\n", 448 | "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", 449 | "numba 0.56.4 requires numpy<1.24,>=1.18, but you have numpy 1.25.2 which is incompatible.\n", 450 | "tensorflow 2.13.0 requires numpy<=1.24.3,>=1.22, but you have numpy 1.25.2 which is incompatible.\n", 451 | "tensorflow 2.13.0 requires typing-extensions<4.6.0,>=3.6.6, but you have typing-extensions 4.7.1 which is incompatible.\u001b[0m\u001b[31m\n", 452 | "\u001b[0mSuccessfully installed diskcache-5.6.3 llama-cpp-python-0.1.77 numpy-1.25.2 typing-extensions-4.7.1\n" 453 | ] 454 | } 455 | ], 456 | "source": [ 457 | "# 安裝特定版本的 llama-cpp-python 套件，並啟用 CUDA 的 cuBLAS 功能。\n", 458 | "# `--force-reinstall` 會強制重新安裝，`--upgrade` 會確保安裝最新版本，而 `--no-cache-dir` 會避免使用本地快取，`--verbose` 提供詳細的輸出。\n", 459 | "!CMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" FORCE_CMAKE=1 pip install llama-cpp-python==0.1.77 --force-reinstall --upgrade --no-cache-dir --verbose" 460 | ] 461 | }, 462 | { 463 | "cell_type": "code", 464 | "execution_count": 5, 465 | "metadata": { 466 | "colab": { 467 | "base_uri": "https://localhost:8080/" 468 | }, 469 | "id": "dRoUDXE666sk", 470 | "outputId": "a0d532e9-2f64-470c-94a7-d3d9f416501a" 471 | }, 472 | "outputs": [ 473 | { 474 | "name": "stdout", 475 | "output_type": "stream", 476 | "text": [ 477 | "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.16.4)\n", 478 | "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (3.12.2)\n", 479 | "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2023.6.0)\n", 480 | "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2.31.0)\n", 481 | "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.66.1)\n", 482 | "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (6.0.1)\n", 483 | "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.7.1)\n", 484 | "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (23.1)\n", 485 | "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.2.0)\n", 486 | "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.4)\n", 487 | "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2.0.4)\n", 488 | "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2023.7.22)\n" 489 | ] 490 | } 491 | ], 492 | "source": [ 493 | "# 安裝 huggingface_hub 套件，此套件可支援與 Hugging Face Model Hub 進行交互。\n", 494 | "!pip install huggingface_hub" 495 | ] 496 | }, 497 | { 498 | "cell_type": "markdown", 499 | "metadata": { 500 | "id": "k7ye1-jg7x8r" 501 | }, 502 | "source": [ 503 | "## Step 2: Download GGML Model and predict the result" 504 | ] 505 | }, 506 | { 507 | "cell_type": "code", 508 | "execution_count": 6, 509 | "metadata": { 510 | "id": "u4LMufzw6jUU" 511 | }, 512 | "outputs": [], 513 | "source": [ 514 | "import json\n", 515 | "import logging\n", 516 | "from huggingface_hub import hf_hub_download\n", 517 | "from llama_cpp import Llama\n", 518 | "\n", 519 | "# 設定日誌\n", 520 | "logging.basicConfig(level=logging.INFO,\n", 521 | " format='%(asctime)s [%(levelname)s] %(message)s',\n", 522 | " datefmt='%Y-%m-%d %H:%M:%S')\n", 523 | "logger = logging.getLogger(__name__)\n", 524 | "\n", 525 | "class Model:\n", 526 | " def __init__(self):\n", 527 | " self.loaded = False # 模型是否已經加載的標志\n", 528 | " self.lcpp_llm = None # 儲存 Llama 模型的變數\n", 529 | " self.model_path = \"\" # 模型的路徑\n", 530 | "\n", 531 | " def load(self, model_name_or_path = \"TheBloke/Llama-2-13B-chat-GGML\", model_basename = \"llama-2-13b-chat.ggmlv3.q5_1.bin\"):\n", 532 | " # 從 Hugging Face Model Hub 下載模型並設定其路徑\n", 533 | " self.model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)\n", 534 | " logger.info(\"Finish: Load Llama 2 model.\") # 輸出模型加載完成的信息\n", 535 | "\n", 536 | " def predict(self, data):\n", 537 | " # 如果模型還沒有被加載，則加載模型\n", 538 | " if not self.loaded:\n", 539 | " self.loaded = True\n", 540 | " self.lcpp_llm = Llama(\n", 541 | " model_path=self.model_path,\n", 542 | " n_threads=2, # 使用的執行緒數量\n", 543 | " n_batch=1024, # 批次大小\n", 544 | " n_gpu_layers=32 # 使用的GPU層數\n", 545 | " )\n", 546 | " logger.info(\"========== Start ==========\")\n", 547 | " # 將 JSON 字符串反序列化成字典\n", 548 | " data_dict = json.loads(data)\n", 549 | " logger.info(\"Input: {}.\".format(data_dict))\n", 550 | " # 使用 Llama 模型進行預測\n", 551 | " response = self.lcpp_llm(prompt=data_dict['prompt'], max_tokens=data_dict['max_tokens'], temperature=0.5, top_p=0.95, repeat_penalty=1.2, top_k=150, echo=True)\n", 552 | " logger.info(\"Response: {}.\".format(response))\n", 553 | " logger.info(\"========== End ==========\")\n", 554 | "\n", 555 | " return {\"answer\": response[\"choices\"][0][\"text\"]} # 返回模型的預測結果" 556 | ] 557 | }, 558 | { 559 | "cell_type": "code", 560 | "execution_count": 7, 561 | "metadata": { 562 | "colab": { 563 | "base_uri": "https://localhost:8080/" 564 | }, 565 | "id": "uiHZFZGf6kSd", 566 | "outputId": "08c5abec-4bbf-4022-9899-c7dc006aabaa" 567 | }, 568 | "outputs": [ 569 | { 570 | "name": "stderr", 571 | "output_type": "stream", 572 | "text": [ 573 | "AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | VSX = 0 | \n" 574 | ] 575 | }, 576 | { 577 | "data": { 578 | "text/plain": [ 579 | "{'answer': 'test 1'}" 580 | ] 581 | }, 582 | "execution_count": 7, 583 | "metadata": {}, 584 | "output_type": "execute_result" 585 | } 586 | ], 587 | "source": [ 588 | "model_instance = Model()\n", 589 | "model_instance.load(model_name_or_path = GGML_HUGGINGFACE_REPO, model_basename = GGML_HUGGINGFACE_BIN_FILE)\n", 590 | "model_instance.predict(json.dumps({\"prompt\": \"test\", \"max_tokens\": 2}))" 591 | ] 592 | }, 593 | { 594 | "cell_type": "markdown", 595 | "metadata": { 596 | "id": "-W4IKvhb7-E4" 597 | }, 598 | "source": [ 599 | "## Step 3: Build the fastapi service" 600 | ] 601 | }, 602 | { 603 | "cell_type": "code", 604 | "execution_count": 8, 605 | "metadata": { 606 | "id": "BoM5mJIe6kP7" 607 | }, 608 | "outputs": [], 609 | "source": [ 610 | "from fastapi import FastAPI\n", 611 | "from fastapi.middleware.cors import CORSMiddleware\n", 612 | "\n", 613 | "# 初始化 FastAPI 應用\n", 614 | "app = FastAPI()\n", 615 | "\n", 616 | "# 為 FastAPI 應用加入 CORS 中間件，允許跨域請求\n", 617 | "app.add_middleware(\n", 618 | " CORSMiddleware,\n", 619 | " allow_origins=['*'], # 允許所有來源的跨域請求\n", 620 | " allow_credentials=True, # 允許憑證（例如 cookies、HTTP認證）的傳遞\n", 621 | " allow_methods=['*'], # 允許所有的 HTTP 方法\n", 622 | " allow_headers=['*'], # 允許所有的 HTTP 頭部\n", 623 | ")\n", 624 | "\n", 625 | "@app.post(\"/predict\") # 定義一個 POST 路由，用於模型預測\n", 626 | "async def predict_text(json_input: dict): # 接收一個字典格式的 JSON 輸入\n", 627 | " result = model_instance.predict(json.dumps(json_input)) # 使用模型實例進行預測\n", 628 | " return result # 返回預測結果\n" 629 | ] 630 | }, 631 | { 632 | "cell_type": "markdown", 633 | "metadata": { 634 | "id": "bQ7WeIyg8C73" 635 | }, 636 | "source": [ 637 | "## Step 4: Start the fastapi service" 638 | ] 639 | }, 640 | { 641 | "cell_type": "code", 642 | "execution_count": null, 643 | "metadata": { 644 | "colab": { 645 | "base_uri": "https://localhost:8080/" 646 | }, 647 | "id": "sMC363JK82jq", 648 | "outputId": "5ad9e348-8445-4e58-ea28-a861ce64c446" 649 | }, 650 | "outputs": [ 651 | { 652 | "name": "stderr", 653 | "output_type": "stream", 654 | "text": [ 655 | "WARNING:pyngrok.process.ngrok:t=2023-09-10T03:10:08+0000 lvl=warn msg=\"ngrok config file found at legacy location, move to XDG location\" xdg_path=/root/.config/ngrok/ngrok.yml legacy_path=/root/.ngrok2/ngrok.yml\n", 656 | "INFO: Started server process [3121]\n", 657 | "INFO: Waiting for application startup.\n", 658 | "INFO: Application startup complete.\n", 659 | "INFO: Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)\n" 660 | ] 661 | }, 662 | { 663 | "name": "stdout", 664 | "output_type": "stream", 665 | "text": [ 666 | "Public URL: https://f1b8-35-184-42-82.ngrok-free.app\n", 667 | "You can use https://f1b8-35-184-42-82.ngrok-free.app/predict to get the assistant result.\n" 668 | ] 669 | }, 670 | { 671 | "name": "stderr", 672 | "output_type": "stream", 673 | "text": [ 674 | "Llama.generate: prefix-match hit\n" 675 | ] 676 | }, 677 | { 678 | "name": "stdout", 679 | "output_type": "stream", 680 | "text": [ 681 | "INFO: 112.104.26.9:0 - \"POST /predict HTTP/1.1\" 200 OK\n" 682 | ] 683 | } 684 | ], 685 | "source": [ 686 | "import nest_asyncio\n", 687 | "from pyngrok import ngrok\n", 688 | "import uvicorn\n", 689 | "\n", 690 | "# 設定 ngrok 的授權令牌\n", 691 | "if NGROK_TOKEN is not None:\n", 692 | " ngrok.set_auth_token(NGROK_TOKEN)\n", 693 | "\n", 694 | "# 建立與 ngrok 的隧道，使外部可以訪問本地的 8000 端口\n", 695 | "ngrok_tunnel = ngrok.connect(8000)\n", 696 | "public_url = ngrok_tunnel.public_url\n", 697 | "\n", 698 | "print('Public URL:', public_url) # 輸出公開的 URL\n", 699 | "print(\"You can use {}/predict to get the assistant result.\".format(public_url))\n", 700 | "\n", 701 | "\n", 702 | "# 使用 nest_asyncio 修正異步事件循環的問題\n", 703 | "nest_asyncio.apply()\n", 704 | "\n", 705 | "# 啟動 uvicorn 伺服器，使 FastAPI 應用運行在 8000 端口\n", 706 | "uvicorn.run(app, port=8000)\n" 707 | ] 708 | }, 709 | { 710 | "cell_type": "markdown", 711 | "metadata": {}, 712 | "source": [ 713 | "### Example CURL command line:\n", 714 | "\n", 715 | "```bash\n", 716 | "curl --location 'https://f1b8-35-184-42-82.ngrok-free.app/predict' \\\n", 717 | "--header 'Content-Type: application/json' \\\n", 718 | "--data '{\"prompt\": \"test\", \"max_tokens\": 2}'\n", 719 | "```" 720 | ] 721 | } 722 | ], 723 | "metadata": { 724 | "accelerator": "GPU", 725 | "colab": { 726 | "gpuType": "T4", 727 | "provenance": [] 728 | }, 729 | "kernelspec": { 730 | "display_name": "Python 3", 731 | "name": "python3" 732 | }, 733 | "language_info": { 734 | "name": "python" 735 | } 736 | }, 737 | "nbformat": 4, 738 | "nbformat_minor": 0 739 | } 740 | -------------------------------------------------------------------------------- /demo-1-llama_gguf_prediction.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "nbformat": 4, 3 | "nbformat_minor": 0, 4 | "metadata": { 5 | "colab": { 6 | "provenance": [], 7 | "gpuType": "T4" 8 | }, 9 | "kernelspec": { 10 | "name": "python3", 11 | "display_name": "Python 3" 12 | }, 13 | "language_info": { 14 | "name": "python" 15 | }, 16 | "accelerator": "GPU", 17 | "widgets": { 18 | "application/vnd.jupyter.widget-state+json": { 19 | "4bb480c16b9a41bfa0227ec094e1415c": { 20 | "model_module": "@jupyter-widgets/controls", 21 | "model_name": "HBoxModel", 22 | "model_module_version": "1.5.0", 23 | "state": { 24 | "_dom_classes": [], 25 | "_model_module": "@jupyter-widgets/controls", 26 | "_model_module_version": "1.5.0", 27 | "_model_name": "HBoxModel", 28 | "_view_count": null, 29 | "_view_module": "@jupyter-widgets/controls", 30 | "_view_module_version": "1.5.0", 31 | "_view_name": "HBoxView", 32 | "box_style": "", 33 | "children": [ 34 | "IPY_MODEL_f145b14de79340328e6ae0c561deea89", 35 | "IPY_MODEL_5131d58c260842ccbbf663b493a34c81", 36 | "IPY_MODEL_b1d81c8ad8bd40358f5f9b0f731d14df" 37 | ], 38 | "layout": "IPY_MODEL_e5c6918b22af4407ad5a4498342ed8f0" 39 | } 40 | }, 41 | "f145b14de79340328e6ae0c561deea89": { 42 | "model_module": "@jupyter-widgets/controls", 43 | "model_name": "HTMLModel", 44 | "model_module_version": "1.5.0", 45 | "state": { 46 | "_dom_classes": [], 47 | "_model_module": "@jupyter-widgets/controls", 48 | "_model_module_version": "1.5.0", 49 | "_model_name": "HTMLModel", 50 | "_view_count": null, 51 | "_view_module": "@jupyter-widgets/controls", 52 | "_view_module_version": "1.5.0", 53 | "_view_name": "HTMLView", 54 | "description": "", 55 | "description_tooltip": null, 56 | "layout": "IPY_MODEL_56a77d51814a4d418ed6b8c148808ac6", 57 | "placeholder": "​", 58 | "style": "IPY_MODEL_2c7ad5881e684b9894c6e6a6f573fd22", 59 | "value": "Taiwan-LLM-7B-v2.1-chat-Q5_1.gguf: 100%" 60 | } 61 | }, 62 | "5131d58c260842ccbbf663b493a34c81": { 63 | "model_module": "@jupyter-widgets/controls", 64 | "model_name": "FloatProgressModel", 65 | "model_module_version": "1.5.0", 66 | "state": { 67 | "_dom_classes": [], 68 | "_model_module": "@jupyter-widgets/controls", 69 | "_model_module_version": "1.5.0", 70 | "_model_name": "FloatProgressModel", 71 | "_view_count": null, 72 | "_view_module": "@jupyter-widgets/controls", 73 | "_view_module_version": "1.5.0", 74 | "_view_name": "ProgressView", 75 | "bar_style": "success", 76 | "description": "", 77 | "description_tooltip": null, 78 | "layout": "IPY_MODEL_a6b32ef03b5344e6bc9b3cb76647dba3", 79 | "max": 5064634208, 80 | "min": 0, 81 | "orientation": "horizontal", 82 | "style": "IPY_MODEL_15a5e9800661418c85f7edba054fa0bc", 83 | "value": 5064634208 84 | } 85 | }, 86 | "b1d81c8ad8bd40358f5f9b0f731d14df": { 87 | "model_module": "@jupyter-widgets/controls", 88 | "model_name": "HTMLModel", 89 | "model_module_version": "1.5.0", 90 | "state": { 91 | "_dom_classes": [], 92 | "_model_module": "@jupyter-widgets/controls", 93 | "_model_module_version": "1.5.0", 94 | "_model_name": "HTMLModel", 95 | "_view_count": null, 96 | "_view_module": "@jupyter-widgets/controls", 97 | "_view_module_version": "1.5.0", 98 | "_view_name": "HTMLView", 99 | "description": "", 100 | "description_tooltip": null, 101 | "layout": "IPY_MODEL_77b4ce39574449e2a6d635bb536d943f", 102 | "placeholder": "​", 103 | "style": "IPY_MODEL_33dba6865d7b4d38b0c6fa09f8a443e8", 104 | "value": " 5.06G/5.06G [01:00<00:00, 85.1MB/s]" 105 | } 106 | }, 107 | "e5c6918b22af4407ad5a4498342ed8f0": { 108 | "model_module": "@jupyter-widgets/base", 109 | "model_name": "LayoutModel", 110 | "model_module_version": "1.2.0", 111 | "state": { 112 | "_model_module": "@jupyter-widgets/base", 113 | "_model_module_version": "1.2.0", 114 | "_model_name": "LayoutModel", 115 | "_view_count": null, 116 | "_view_module": "@jupyter-widgets/base", 117 | "_view_module_version": "1.2.0", 118 | "_view_name": "LayoutView", 119 | "align_content": null, 120 | "align_items": null, 121 | "align_self": null, 122 | "border": null, 123 | "bottom": null, 124 | "display": null, 125 | "flex": null, 126 | "flex_flow": null, 127 | "grid_area": null, 128 | "grid_auto_columns": null, 129 | "grid_auto_flow": null, 130 | "grid_auto_rows": null, 131 | "grid_column": null, 132 | "grid_gap": null, 133 | "grid_row": null, 134 | "grid_template_areas": null, 135 | "grid_template_columns": null, 136 | "grid_template_rows": null, 137 | "height": null, 138 | "justify_content": null, 139 | "justify_items": null, 140 | "left": null, 141 | "margin": null, 142 | "max_height": null, 143 | "max_width": null, 144 | "min_height": null, 145 | "min_width": null, 146 | "object_fit": null, 147 | "object_position": null, 148 | "order": null, 149 | "overflow": null, 150 | "overflow_x": null, 151 | "overflow_y": null, 152 | "padding": null, 153 | "right": null, 154 | "top": null, 155 | "visibility": null, 156 | "width": null 157 | } 158 | }, 159 | "56a77d51814a4d418ed6b8c148808ac6": { 160 | "model_module": "@jupyter-widgets/base", 161 | "model_name": "LayoutModel", 162 | "model_module_version": "1.2.0", 163 | "state": { 164 | "_model_module": "@jupyter-widgets/base", 165 | "_model_module_version": "1.2.0", 166 | "_model_name": "LayoutModel", 167 | "_view_count": null, 168 | "_view_module": "@jupyter-widgets/base", 169 | "_view_module_version": "1.2.0", 170 | "_view_name": "LayoutView", 171 | "align_content": null, 172 | "align_items": null, 173 | "align_self": null, 174 | "border": null, 175 | "bottom": null, 176 | "display": null, 177 | "flex": null, 178 | "flex_flow": null, 179 | "grid_area": null, 180 | "grid_auto_columns": null, 181 | "grid_auto_flow": null, 182 | "grid_auto_rows": null, 183 | "grid_column": null, 184 | "grid_gap": null, 185 | "grid_row": null, 186 | "grid_template_areas": null, 187 | "grid_template_columns": null, 188 | "grid_template_rows": null, 189 | "height": null, 190 | "justify_content": null, 191 | "justify_items": null, 192 | "left": null, 193 | "margin": null, 194 | "max_height": null, 195 | "max_width": null, 196 | "min_height": null, 197 | "min_width": null, 198 | "object_fit": null, 199 | "object_position": null, 200 | "order": null, 201 | "overflow": null, 202 | "overflow_x": null, 203 | "overflow_y": null, 204 | "padding": null, 205 | "right": null, 206 | "top": null, 207 | "visibility": null, 208 | "width": null 209 | } 210 | }, 211 | "2c7ad5881e684b9894c6e6a6f573fd22": { 212 | "model_module": "@jupyter-widgets/controls", 213 | "model_name": "DescriptionStyleModel", 214 | "model_module_version": "1.5.0", 215 | "state": { 216 | "_model_module": "@jupyter-widgets/controls", 217 | "_model_module_version": "1.5.0", 218 | "_model_name": "DescriptionStyleModel", 219 | "_view_count": null, 220 | "_view_module": "@jupyter-widgets/base", 221 | "_view_module_version": "1.2.0", 222 | "_view_name": "StyleView", 223 | "description_width": "" 224 | } 225 | }, 226 | "a6b32ef03b5344e6bc9b3cb76647dba3": { 227 | "model_module": "@jupyter-widgets/base", 228 | "model_name": "LayoutModel", 229 | "model_module_version": "1.2.0", 230 | "state": { 231 | "_model_module": "@jupyter-widgets/base", 232 | "_model_module_version": "1.2.0", 233 | "_model_name": "LayoutModel", 234 | "_view_count": null, 235 | "_view_module": "@jupyter-widgets/base", 236 | "_view_module_version": "1.2.0", 237 | "_view_name": "LayoutView", 238 | "align_content": null, 239 | "align_items": null, 240 | "align_self": null, 241 | "border": null, 242 | "bottom": null, 243 | "display": null, 244 | "flex": null, 245 | "flex_flow": null, 246 | "grid_area": null, 247 | "grid_auto_columns": null, 248 | "grid_auto_flow": null, 249 | "grid_auto_rows": null, 250 | "grid_column": null, 251 | "grid_gap": null, 252 | "grid_row": null, 253 | "grid_template_areas": null, 254 | "grid_template_columns": null, 255 | "grid_template_rows": null, 256 | "height": null, 257 | "justify_content": null, 258 | "justify_items": null, 259 | "left": null, 260 | "margin": null, 261 | "max_height": null, 262 | "max_width": null, 263 | "min_height": null, 264 | "min_width": null, 265 | "object_fit": null, 266 | "object_position": null, 267 | "order": null, 268 | "overflow": null, 269 | "overflow_x": null, 270 | "overflow_y": null, 271 | "padding": null, 272 | "right": null, 273 | "top": null, 274 | "visibility": null, 275 | "width": null 276 | } 277 | }, 278 | "15a5e9800661418c85f7edba054fa0bc": { 279 | "model_module": "@jupyter-widgets/controls", 280 | "model_name": "ProgressStyleModel", 281 | "model_module_version": "1.5.0", 282 | "state": { 283 | "_model_module": "@jupyter-widgets/controls", 284 | "_model_module_version": "1.5.0", 285 | "_model_name": "ProgressStyleModel", 286 | "_view_count": null, 287 | "_view_module": "@jupyter-widgets/base", 288 | "_view_module_version": "1.2.0", 289 | "_view_name": "StyleView", 290 | "bar_color": null, 291 | "description_width": "" 292 | } 293 | }, 294 | "77b4ce39574449e2a6d635bb536d943f": { 295 | "model_module": "@jupyter-widgets/base", 296 | "model_name": "LayoutModel", 297 | "model_module_version": "1.2.0", 298 | "state": { 299 | "_model_module": "@jupyter-widgets/base", 300 | "_model_module_version": "1.2.0", 301 | "_model_name": "LayoutModel", 302 | "_view_count": null, 303 | "_view_module": "@jupyter-widgets/base", 304 | "_view_module_version": "1.2.0", 305 | "_view_name": "LayoutView", 306 | "align_content": null, 307 | "align_items": null, 308 | "align_self": null, 309 | "border": null, 310 | "bottom": null, 311 | "display": null, 312 | "flex": null, 313 | "flex_flow": null, 314 | "grid_area": null, 315 | "grid_auto_columns": null, 316 | "grid_auto_flow": null, 317 | "grid_auto_rows": null, 318 | "grid_column": null, 319 | "grid_gap": null, 320 | "grid_row": null, 321 | "grid_template_areas": null, 322 | "grid_template_columns": null, 323 | "grid_template_rows": null, 324 | "height": null, 325 | "justify_content": null, 326 | "justify_items": null, 327 | "left": null, 328 | "margin": null, 329 | "max_height": null, 330 | "max_width": null, 331 | "min_height": null, 332 | "min_width": null, 333 | "object_fit": null, 334 | "object_position": null, 335 | "order": null, 336 | "overflow": null, 337 | "overflow_x": null, 338 | "overflow_y": null, 339 | "padding": null, 340 | "right": null, 341 | "top": null, 342 | "visibility": null, 343 | "width": null 344 | } 345 | }, 346 | "33dba6865d7b4d38b0c6fa09f8a443e8": { 347 | "model_module": "@jupyter-widgets/controls", 348 | "model_name": "DescriptionStyleModel", 349 | "model_module_version": "1.5.0", 350 | "state": { 351 | "_model_module": "@jupyter-widgets/controls", 352 | "_model_module_version": "1.5.0", 353 | "_model_name": "DescriptionStyleModel", 354 | "_view_count": null, 355 | "_view_module": "@jupyter-widgets/base", 356 | "_view_module_version": "1.2.0", 357 | "_view_name": "StyleView", 358 | "description_width": "" 359 | } 360 | } 361 | } 362 | } 363 | }, 364 | "cells": [ 365 | { 366 | "cell_type": "markdown", 367 | "source": [ 368 | "# Llama 2 gguf Example\n", 369 | "推薦至少使用 T4 GPU 來作為你的服務啟用" 370 | ], 371 | "metadata": { 372 | "id": "sBv4jxXPJKha" 373 | } 374 | }, 375 | { 376 | "cell_type": "markdown", 377 | "source": [ 378 | "## Step 0: Config Setting" 379 | ], 380 | "metadata": { 381 | "id": "SUIz08O8NPsp" 382 | } 383 | }, 384 | { 385 | "cell_type": "code", 386 | "source": [ 387 | "GGUF_HUGGINGFACE_REPO = \"audreyt/Taiwan-LLM-7B-v2.1-chat-GGUF\"\n", 388 | "GGUF_HUGGINGFACE_BIN_FILE = \"Taiwan-LLM-7B-v2.1-chat-Q5_1.gguf\"" 389 | ], 390 | "metadata": { 391 | "id": "64oUtFgwGko8" 392 | }, 393 | "execution_count": 1, 394 | "outputs": [] 395 | }, 396 | { 397 | "cell_type": "markdown", 398 | "source": [ 399 | "## Step 1: Install python package\n" 400 | ], 401 | "metadata": { 402 | "id": "Wz_9tYIBNYwj" 403 | } 404 | }, 405 | { 406 | "cell_type": "code", 407 | "execution_count": 2, 408 | "metadata": { 409 | "colab": { 410 | "base_uri": "https://localhost:8080/" 411 | }, 412 | "id": "fSwCrQsEEAtm", 413 | "outputId": "205fbf85-95b9-4d51-e3fb-caa75c0448dd" 414 | }, 415 | "outputs": [ 416 | { 417 | "output_type": "stream", 418 | "name": "stdout", 419 | "text": [ 420 | "Using pip 23.1.2 from /usr/local/lib/python3.10/dist-packages/pip (python 3.10)\n", 421 | "Collecting llama-cpp-python==0.2.26\n", 422 | " Downloading llama_cpp_python-0.2.26.tar.gz (8.8 MB)\n", 423 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.8/8.8 MB\u001b[0m \u001b[31m24.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 424 | "\u001b[?25h Running command pip subprocess to install build dependencies\n", 425 | " Using pip 23.1.2 from /usr/local/lib/python3.10/dist-packages/pip (python 3.10)\n", 426 | " Collecting scikit-build-core[pyproject]>=0.5.1\n", 427 | " Downloading scikit_build_core-0.7.0-py3-none-any.whl (136 kB)\n", 428 | " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 136.6/136.6 kB 2.2 MB/s eta 0:00:00\n", 429 | " Collecting exceptiongroup (from scikit-build-core[pyproject]>=0.5.1)\n", 430 | " Downloading exceptiongroup-1.2.0-py3-none-any.whl (16 kB)\n", 431 | " Collecting packaging>=20.9 (from scikit-build-core[pyproject]>=0.5.1)\n", 432 | " Downloading packaging-23.2-py3-none-any.whl (53 kB)\n", 433 | " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 53.0/53.0 kB 3.6 MB/s eta 0:00:00\n", 434 | " Collecting tomli>=1.1 (from scikit-build-core[pyproject]>=0.5.1)\n", 435 | " Downloading tomli-2.0.1-py3-none-any.whl (12 kB)\n", 436 | " Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]>=0.5.1)\n", 437 | " Downloading pathspec-0.12.1-py3-none-any.whl (31 kB)\n", 438 | " Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]>=0.5.1)\n", 439 | " Downloading pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB)\n", 440 | " Installing collected packages: tomli, pathspec, packaging, exceptiongroup, scikit-build-core, pyproject-metadata\n", 441 | " ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", 442 | " lida 0.0.10 requires fastapi, which is not installed.\n", 443 | " lida 0.0.10 requires kaleido, which is not installed.\n", 444 | " lida 0.0.10 requires python-multipart, which is not installed.\n", 445 | " lida 0.0.10 requires uvicorn, which is not installed.\n", 446 | " Successfully installed exceptiongroup-1.2.0 packaging-23.2 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.7.0 tomli-2.0.1\n", 447 | " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", 448 | " Running command Getting requirements to build wheel\n", 449 | " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", 450 | " Running command pip subprocess to install backend dependencies\n", 451 | " Using pip 23.1.2 from /usr/local/lib/python3.10/dist-packages/pip (python 3.10)\n", 452 | " Collecting cmake>=3.21\n", 453 | " Downloading cmake-3.28.1-py2.py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (26.3 MB)\n", 454 | " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 26.3/26.3 MB 17.6 MB/s eta 0:00:00\n", 455 | " Collecting ninja>=1.5\n", 456 | " Downloading ninja-1.11.1.1-py2.py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl (307 kB)\n", 457 | " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 307.2/307.2 kB 15.9 MB/s eta 0:00:00\n", 458 | " Installing collected packages: ninja, cmake\n", 459 | " Creating /tmp/pip-build-env-mmxt792p/normal/local/bin\n", 460 | " changing mode of /tmp/pip-build-env-mmxt792p/normal/local/bin/ninja to 755\n", 461 | " changing mode of /tmp/pip-build-env-mmxt792p/normal/local/bin/cmake to 755\n", 462 | " changing mode of /tmp/pip-build-env-mmxt792p/normal/local/bin/cpack to 755\n", 463 | " changing mode of /tmp/pip-build-env-mmxt792p/normal/local/bin/ctest to 755\n", 464 | " Successfully installed cmake-3.28.1 ninja-1.11.1.1\n", 465 | " Installing backend dependencies ... \u001b[?25l\u001b[?25hdone\n", 466 | " Running command Preparing metadata (pyproject.toml)\n", 467 | " *** scikit-build-core 0.7.0 using CMake 3.28.1 (metadata_wheel)\n", 468 | " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", 469 | "Collecting typing-extensions>=4.5.0 (from llama-cpp-python==0.2.26)\n", 470 | " Downloading typing_extensions-4.9.0-py3-none-any.whl (32 kB)\n", 471 | "Collecting numpy>=1.20.0 (from llama-cpp-python==0.2.26)\n", 472 | " Downloading numpy-1.26.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.2 MB)\n", 473 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.2/18.2 MB\u001b[0m \u001b[31m146.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 474 | "\u001b[?25hCollecting diskcache>=5.6.1 (from llama-cpp-python==0.2.26)\n", 475 | " Downloading diskcache-5.6.3-py3-none-any.whl (45 kB)\n", 476 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.5/45.5 kB\u001b[0m \u001b[31m163.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 477 | "\u001b[?25hBuilding wheels for collected packages: llama-cpp-python\n", 478 | " Running command Building wheel for llama-cpp-python (pyproject.toml)\n", 479 | " *** scikit-build-core 0.7.0 using CMake 3.28.1 (wheel)\n", 480 | " *** Configuring CMake...\n", 481 | " loading initial cache file /tmp/tmp6qatxtsg/build/CMakeInit.txt\n", 482 | " -- The C compiler identification is GNU 11.4.0\n", 483 | " -- The CXX compiler identification is GNU 11.4.0\n", 484 | " -- Detecting C compiler ABI info\n", 485 | " -- Detecting C compiler ABI info - done\n", 486 | " -- Check for working C compiler: /usr/bin/cc - skipped\n", 487 | " -- Detecting C compile features\n", 488 | " -- Detecting C compile features - done\n", 489 | " -- Detecting CXX compiler ABI info\n", 490 | " -- Detecting CXX compiler ABI info - done\n", 491 | " -- Check for working CXX compiler: /usr/bin/c++ - skipped\n", 492 | " -- Detecting CXX compile features\n", 493 | " -- Detecting CXX compile features - done\n", 494 | " -- Found Git: /usr/bin/git (found version \"2.34.1\")\n", 495 | " -- Performing Test CMAKE_HAVE_LIBC_PTHREAD\n", 496 | " -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success\n", 497 | " -- Found Threads: TRUE\n", 498 | " -- Found CUDAToolkit: /usr/local/cuda/targets/x86_64-linux/include (found version \"12.2.140\")\n", 499 | " -- cuBLAS found\n", 500 | " -- The CUDA compiler identification is NVIDIA 12.2.140\n", 501 | " -- Detecting CUDA compiler ABI info\n", 502 | " -- Detecting CUDA compiler ABI info - done\n", 503 | " -- Check for working CUDA compiler: /usr/local/cuda/bin/nvcc - skipped\n", 504 | " -- Detecting CUDA compile features\n", 505 | " -- Detecting CUDA compile features - done\n", 506 | " -- Using CUDA architectures: 52;61;70\n", 507 | " -- CUDA host compiler is GNU 11.4.0\n", 508 | "\n", 509 | " -- CMAKE_SYSTEM_PROCESSOR: x86_64\n", 510 | " -- x86 detected\n", 511 | " CMake Warning (dev) at CMakeLists.txt:21 (install):\n", 512 | " Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION.\n", 513 | " This warning is for project developers. Use -Wno-dev to suppress it.\n", 514 | "\n", 515 | " CMake Warning (dev) at CMakeLists.txt:30 (install):\n", 516 | " Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION.\n", 517 | " This warning is for project developers. Use -Wno-dev to suppress it.\n", 518 | "\n", 519 | " -- Configuring done (4.2s)\n", 520 | " -- Generating done (0.0s)\n", 521 | " -- Build files have been written to: /tmp/tmp6qatxtsg/build\n", 522 | " *** Building project with Ninja...\n", 523 | " Change Dir: '/tmp/tmp6qatxtsg/build'\n", 524 | "\n", 525 | " Run Build Command(s): /tmp/pip-build-env-mmxt792p/normal/local/lib/python3.10/dist-packages/ninja/data/bin/ninja -v\n", 526 | " [1/23] /usr/bin/cc -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -march=native -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/ggml-alloc.c\n", 527 | " [2/23] /usr/bin/cc -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -march=native -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/ggml-backend.c\n", 528 | " [3/23] /usr/bin/cc -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -march=native -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/ggml-quants.c\n", 529 | " [4/23] /usr/bin/cc -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -march=native -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/ggml.c\n", 530 | " [5/23] cd /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp && /tmp/pip-build-env-mmxt792p/normal/local/lib/python3.10/dist-packages/cmake/data/bin/cmake -DMSVC= -DCMAKE_C_COMPILER_VERSION=11.4.0 -DCMAKE_C_COMPILER_ID=GNU -DCMAKE_VS_PLATFORM_NAME= -DCMAKE_C_COMPILER=/usr/bin/cc -P /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake\n", 531 | " -- Found Git: /usr/bin/git (found version \"2.34.1\")\n", 532 | " [6/23] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -march=native -MD -MT vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/build-info.cpp\n", 533 | " [7/23] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -march=native -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/common.cpp\n", 534 | " [8/23] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -march=native -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/sampling.cpp\n", 535 | " [9/23] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -march=native -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/console.cpp\n", 536 | " [10/23] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -march=native -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/grammar-parser.cpp\n", 537 | " [11/23] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -DLLAMA_BUILD -DLLAMA_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dllama_EXPORTS -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -march=native -MD -MT vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -MF vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o.d -o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/llama.cpp\n", 538 | " [12/23] /usr/bin/c++ -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -march=native -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/train.cpp\n", 539 | " [13/23] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -fPIC -Wno-cast-qual -MD -MT vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o -MF vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o.d -o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/llava.cpp\n", 540 | " [14/23] /usr/bin/c++ -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/common/. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/../../common -O3 -DNDEBUG -MD -MT vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o -MF vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o.d -o vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/llava-cli.cpp\n", 541 | " [15/23] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -fPIC -Wno-cast-qual -MD -MT vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o -MF vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o.d -o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/examples/llava/clip.cpp\n", 542 | " [16/23] : && /tmp/pip-build-env-mmxt792p/normal/local/lib/python3.10/dist-packages/cmake/data/bin/cmake -E rm -f vendor/llama.cpp/examples/llava/libllava_static.a && /usr/bin/ar qc vendor/llama.cpp/examples/llava/libllava_static.a vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o && /usr/bin/ranlib vendor/llama.cpp/examples/llava/libllava_static.a && :\n", 543 | " [17/23] /usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_USE_CUBLAS -DK_QUANTS_PER_ITERATION=2 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/. -isystem /usr/local/cuda/targets/x86_64-linux/include -O3 -DNDEBUG -std=c++11 \"--generate-code=arch=compute_52,code=[compute_52,sm_52]\" \"--generate-code=arch=compute_61,code=[compute_61,sm_61]\" \"--generate-code=arch=compute_70,code=[compute_70,sm_70]\" -Xcompiler=-fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -use_fast_math -Wno-pedantic -Xcompiler \"-Wno-array-bounds -Wno-format-truncation -Wextra-semi\" -march=native -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o.d -x cu -c /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/vendor/llama.cpp/ggml-cuda.cu -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o\n", 544 | " [18/23] : && /usr/bin/g++ -fPIC -shared -Wl,-soname,libggml_shared.so -o vendor/llama.cpp/libggml_shared.so vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda/targets/x86_64-linux/lib/stubs/libcuda.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libculibos.a -lcudadevrt -lcudart_static -lrt -lpthread -ldl -L\"/usr/local/cuda/targets/x86_64-linux/lib/stubs\" -L\"/usr/local/cuda/targets/x86_64-linux/lib\" && :\n", 545 | " [19/23] : && /tmp/pip-build-env-mmxt792p/normal/local/lib/python3.10/dist-packages/cmake/data/bin/cmake -E rm -f vendor/llama.cpp/libggml_static.a && /usr/bin/ar qc vendor/llama.cpp/libggml_static.a vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o && /usr/bin/ranlib vendor/llama.cpp/libggml_static.a && :\n", 546 | " [20/23] : && /usr/bin/c++ -fPIC -O3 -DNDEBUG -shared -Wl,-soname,libllama.so -o vendor/llama.cpp/libllama.so vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -L/usr/local/cuda/targets/x86_64-linux/lib -Wl,-rpath,/usr/local/cuda-12.2/targets/x86_64-linux/lib: /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda/targets/x86_64-linux/lib/stubs/libcuda.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libculibos.a -lcudadevrt -lcudart_static -lrt -lpthread -ldl && :\n", 547 | " [21/23] : && /tmp/pip-build-env-mmxt792p/normal/local/lib/python3.10/dist-packages/cmake/data/bin/cmake -E rm -f vendor/llama.cpp/common/libcommon.a && /usr/bin/ar qc vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o && /usr/bin/ranlib vendor/llama.cpp/common/libcommon.a && :\n", 548 | " [22/23] : && /usr/bin/c++ -fPIC -O3 -DNDEBUG -shared -Wl,-soname,libllava.so -o vendor/llama.cpp/examples/llava/libllava.so vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-cuda.cu.o -Wl,-rpath,/tmp/tmp6qatxtsg/build/vendor/llama.cpp:/usr/local/cuda-12.2/targets/x86_64-linux/lib: vendor/llama.cpp/libllama.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libculibos.a /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda/targets/x86_64-linux/lib/stubs/libcuda.so && :\n", 549 | " [23/23] : && /usr/bin/c++ -O3 -DNDEBUG vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o -o vendor/llama.cpp/examples/llava/llava-cli -Wl,-rpath,/tmp/tmp6qatxtsg/build/vendor/llama.cpp:/usr/local/cuda-12.2/targets/x86_64-linux/lib: vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/libllama.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-12.2/targets/x86_64-linux/lib/libculibos.a /usr/local/cuda-12.2/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda/targets/x86_64-linux/lib/stubs/libcuda.so && :\n", 550 | "\n", 551 | " *** Installing project into wheel...\n", 552 | " -- Install configuration: \"Release\"\n", 553 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/lib/libggml_shared.so\n", 554 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake\n", 555 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake\n", 556 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/include/ggml.h\n", 557 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/include/ggml-cuda.h\n", 558 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/lib/libllama.so\n", 559 | " -- Set non-toolchain portion of runtime path of \"/tmp/tmp6qatxtsg/wheel/platlib/lib/libllama.so\" to \"\"\n", 560 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/include/llama.h\n", 561 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/bin/convert.py\n", 562 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/bin/convert-lora-to-ggml.py\n", 563 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/llama_cpp/libllama.so\n", 564 | " -- Set non-toolchain portion of runtime path of \"/tmp/tmp6qatxtsg/wheel/platlib/llama_cpp/libllama.so\" to \"\"\n", 565 | " -- Installing: /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/llama_cpp/libllama.so\n", 566 | " -- Set non-toolchain portion of runtime path of \"/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/llama_cpp/libllama.so\" to \"\"\n", 567 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/lib/libllava.so\n", 568 | " -- Set non-toolchain portion of runtime path of \"/tmp/tmp6qatxtsg/wheel/platlib/lib/libllava.so\" to \"\"\n", 569 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/bin/llava-cli\n", 570 | " -- Set non-toolchain portion of runtime path of \"/tmp/tmp6qatxtsg/wheel/platlib/bin/llava-cli\" to \"\"\n", 571 | " -- Installing: /tmp/tmp6qatxtsg/wheel/platlib/llama_cpp/libllava.so\n", 572 | " -- Set non-toolchain portion of runtime path of \"/tmp/tmp6qatxtsg/wheel/platlib/llama_cpp/libllava.so\" to \"\"\n", 573 | " -- Installing: /tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/llama_cpp/libllava.so\n", 574 | " -- Set non-toolchain portion of runtime path of \"/tmp/pip-install-wast9ri8/llama-cpp-python_098752e1fe944b4c88f36b19fee61ca6/llama_cpp/libllava.so\" to \"\"\n", 575 | " *** Making wheel...\n", 576 | " *** Created llama_cpp_python-0.2.26-cp310-cp310-manylinux_2_35_x86_64.whl...\n", 577 | " Building wheel for llama-cpp-python (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", 578 | " Created wheel for llama-cpp-python: filename=llama_cpp_python-0.2.26-cp310-cp310-manylinux_2_35_x86_64.whl size=8129912 sha256=6241094aacd8dc73f7a0133d15c419695f48e0639fa2858590975822dd3a059d\n", 579 | " Stored in directory: /tmp/pip-ephem-wheel-cache-mhfgccsy/wheels/91/80/ce/ac6afea8c1d6fbcec7e14183033a5b2796c742d4f470010c72\n", 580 | "Successfully built llama-cpp-python\n", 581 | "Installing collected packages: typing-extensions, numpy, diskcache, llama-cpp-python\n", 582 | " Attempting uninstall: typing-extensions\n", 583 | " Found existing installation: typing_extensions 4.5.0\n", 584 | " Uninstalling typing_extensions-4.5.0:\n", 585 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/__pycache__/typing_extensions.cpython-310.pyc\n", 586 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/typing_extensions-4.5.0.dist-info/\n", 587 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/typing_extensions.py\n", 588 | " Successfully uninstalled typing_extensions-4.5.0\n", 589 | " Attempting uninstall: numpy\n", 590 | " Found existing installation: numpy 1.23.5\n", 591 | " Uninstalling numpy-1.23.5:\n", 592 | " Removing file or directory /usr/local/bin/f2py\n", 593 | " Removing file or directory /usr/local/bin/f2py3\n", 594 | " Removing file or directory /usr/local/bin/f2py3.10\n", 595 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/numpy-1.23.5.dist-info/\n", 596 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/numpy.libs/\n", 597 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/numpy/\n", 598 | " Successfully uninstalled numpy-1.23.5\n", 599 | " changing mode of /usr/local/bin/f2py to 755\n", 600 | " Attempting uninstall: diskcache\n", 601 | " Found existing installation: diskcache 5.6.3\n", 602 | " Uninstalling diskcache-5.6.3:\n", 603 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/diskcache-5.6.3.dist-info/\n", 604 | " Removing file or directory /usr/local/lib/python3.10/dist-packages/diskcache/\n", 605 | " Successfully uninstalled diskcache-5.6.3\n", 606 | "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", 607 | "lida 0.0.10 requires fastapi, which is not installed.\n", 608 | "lida 0.0.10 requires kaleido, which is not installed.\n", 609 | "lida 0.0.10 requires python-multipart, which is not installed.\n", 610 | "lida 0.0.10 requires uvicorn, which is not installed.\n", 611 | "llmx 0.0.15a0 requires cohere, which is not installed.\n", 612 | "llmx 0.0.15a0 requires openai, which is not installed.\n", 613 | "llmx 0.0.15a0 requires tiktoken, which is not installed.\n", 614 | "tensorflow-probability 0.22.0 requires typing-extensions<4.6.0, but you have typing-extensions 4.9.0 which is incompatible.\u001b[0m\u001b[31m\n", 615 | "\u001b[0mSuccessfully installed diskcache-5.6.3 llama-cpp-python-0.2.26 numpy-1.26.2 typing-extensions-4.9.0\n" 616 | ] 617 | } 618 | ], 619 | "source": [ 620 | "!CMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" FORCE_CMAKE=1 pip install llama-cpp-python==0.2.25 --force-reinstall --upgrade --no-cache-dir --verbose" 621 | ] 622 | }, 623 | { 624 | "cell_type": "code", 625 | "source": [ 626 | "!pip install huggingface_hub" 627 | ], 628 | "metadata": { 629 | "colab": { 630 | "base_uri": "https://localhost:8080/" 631 | }, 632 | "id": "WI4udGDKF9Pe", 633 | "outputId": "a24476f8-7d73-4511-ac72-b9da8132e996" 634 | }, 635 | "execution_count": 3, 636 | "outputs": [ 637 | { 638 | "output_type": "stream", 639 | "name": "stdout", 640 | "text": [ 641 | "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.19.4)\n", 642 | "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (3.13.1)\n", 643 | "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2023.6.0)\n", 644 | "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2.31.0)\n", 645 | "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.66.1)\n", 646 | "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (6.0.1)\n", 647 | "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.9.0)\n", 648 | "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (23.2)\n", 649 | "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.3.2)\n", 650 | "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.6)\n", 651 | "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2.0.7)\n", 652 | "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2023.11.17)\n" 653 | ] 654 | } 655 | ] 656 | }, 657 | { 658 | "cell_type": "markdown", 659 | "source": [ 660 | "## Step 2: Download GGML LLM Model" 661 | ], 662 | "metadata": { 663 | "id": "pbNa1w_SNcaj" 664 | } 665 | }, 666 | { 667 | "cell_type": "code", 668 | "source": [ 669 | "from huggingface_hub import hf_hub_download\n", 670 | "\n", 671 | "model_path = hf_hub_download(repo_id=GGUF_HUGGINGFACE_REPO, filename=GGUF_HUGGINGFACE_BIN_FILE)\n", 672 | "model_path" 673 | ], 674 | "metadata": { 675 | "colab": { 676 | "base_uri": "https://localhost:8080/", 677 | "height": 85, 678 | "referenced_widgets": [ 679 | "4bb480c16b9a41bfa0227ec094e1415c", 680 | "f145b14de79340328e6ae0c561deea89", 681 | "5131d58c260842ccbbf663b493a34c81", 682 | "b1d81c8ad8bd40358f5f9b0f731d14df", 683 | "e5c6918b22af4407ad5a4498342ed8f0", 684 | "56a77d51814a4d418ed6b8c148808ac6", 685 | "2c7ad5881e684b9894c6e6a6f573fd22", 686 | "a6b32ef03b5344e6bc9b3cb76647dba3", 687 | "15a5e9800661418c85f7edba054fa0bc", 688 | "77b4ce39574449e2a6d635bb536d943f", 689 | "33dba6865d7b4d38b0c6fa09f8a443e8" 690 | ] 691 | }, 692 | "id": "kzes1srfF9K9", 693 | "outputId": "8ef73338-79ce-4b01-a344-71bc7f86d7aa" 694 | }, 695 | "execution_count": 4, 696 | "outputs": [ 697 | { 698 | "output_type": "display_data", 699 | "data": { 700 | "text/plain": [ 701 | "Taiwan-LLM-7B-v2.1-chat-Q5_1.gguf: 0%| | 0.00/5.06G [00:00