Add code and env info

chapter01/Chapter 1 - Introduction to Language Models.ipynb

@@ -0,0 +1,152 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "EDe7DsPWmEBV"
+   },
+   "source": [
+    "<h1>Chapter 1 - Introduction to Language Models</h1>\n",
+    "<i>Exploring the exciting field of Language AI</i>\n",
+    "\n",
+    "\n",
+    "<a href=\"https://www.amazon.com/Hands-Large-Language-Models-Understanding/dp/1098150961\"><img src=\"https://img.shields.io/badge/Buy%20the%20Book!-grey?logo=amazon\"></a>\n",
+    "<a href=\"https://www.oreilly.com/library/view/hands-on-large-language/9781098150952/\"><img src=\"https://img.shields.io/badge/O'Reilly-white.svg?logo=data:image/svg%2bxml;base64,PHN2ZyB3aWR0aD0iMzQiIGhlaWdodD0iMjciIHZpZXdCb3g9IjAgMCAzNCAyNyIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KPGNpcmNsZSBjeD0iMTMiIGN5PSIxNCIgcj0iMTEiIHN0cm9rZT0iI0Q0MDEwMSIgc3Ryb2tlLXdpZHRoPSI0Ii8+CjxjaXJjbGUgY3g9IjMwLjUiIGN5PSIzLjUiIHI9IjMuNSIgZmlsbD0iI0Q0MDEwMSIvPgo8L3N2Zz4K\"></a>\n",
+    "<a href=\"https://github.com/HandsOnLLM/Hands-On-Large-Language-Models\"><img src=\"https://img.shields.io/badge/GitHub%20Repository-black?logo=github\"></a>\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1NOo_hNGE8MuXAUa6UXh3eHzt9X_1mYvc?usp=sharing)\n",
+    "\n",
+    "---\n",
+    "\n",
+    "This notebook is for Chapter 1 of the [Hands-On Large Language Models](https://www.amazon.com/Hands-Large-Language-Models-Understanding/dp/1098150961) book by [Jay Alammar](https://www.linkedin.com/in/jalammar) and [Maarten Grootendorst](https://www.linkedin.com/in/mgrootendorst/).\n",
+    "\n",
+    "---\n",
+    "\n",
+    "<a href=\"https://www.amazon.com/Hands-Large-Language-Models-Understanding/dp/1098150961\">\n",
+    "<img src=\"https://raw.githubusercontent.com/HandsOnLLM/Hands-On-Large-Language-Models/main/images/book_cover.png\" width=\"350\"/></a>\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "hXp09JFsFBXi"
+   },
+   "source": [
+    "# Phi-3\n",
+    "\n",
+    "The first step is to load our model onto the GPU for faster inference. Note that we load the model and tokenizer separately (although that isn't always necessary)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "id": "RSNalRXZyTTk"
+   },
+   "outputs": [],
+   "source": [
+    "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
+    "\n",
+    "# Load model and tokenizer\n",
+    "model = AutoModelForCausalLM.from_pretrained(\n",
+    "    \"microsoft/Phi-3-mini-4k-instruct\",\n",
+    "    device_map=\"cuda\",\n",
+    "    torch_dtype=\"auto\",\n",
+    "    trust_remote_code=True,\n",
+    ")\n",
+    "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/Phi-3-mini-4k-instruct\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "qdyYYS0E5fEU"
+   },
+   "source": [
+    "Although we can now use the model and tokenizer directly, it's much easier to wrap it in a `pipeline` object:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "DiUi4Wu1FCyN"
+   },
+   "outputs": [],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "# Create a pipeline\n",
+    "generator = pipeline(\n",
+    "    \"text-generation\",\n",
+    "    model=model,\n",
+    "    tokenizer=tokenizer,\n",
+    "    return_full_text=False,\n",
+    "    max_new_tokens=500,\n",
+    "    do_sample=False\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "mD49kysT5mMY"
+   },
+   "source": [
+    "Finally, we create our prompt as a user and give it to the model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "hkR7LBmiyXmY"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Why did the chicken join the band? Because it had the drumsticks!\n"
+     ]
+    }
+   ],
+   "source": [
+    "# The prompt (user input / query)\n",
+    "messages = [\n",
+    "    {\"role\": \"user\", \"content\": \"Create a funny joke about chickens.\"}\n",
+    "]\n",
+    "\n",
+    "# Generate output\n",
+    "output = generator(messages)\n",
+    "print(output[0][\"generated_text\"])"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "authorship_tag": "ABX9TyPCWg08aO4e8NWQuYCK5ppF",
+   "gpuType": "T4",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.14"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

environment.yml

@@ -0,0 +1,248 @@
+name: thellmbook
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - bzip2=1.0.8
+  - ca-certificates=2024.8.30
+  - libffi=3.4.2
+  - libsqlite=3.46.1
+  - libzlib=1.3.1
+  - openssl=3.3.2
+  - pip=24.2
+  - python=3.10.14
+  - setuptools=73.0.1
+  - tk=8.6.13
+  - ucrt=10.0.22621.0
+  - vc=14.3
+  - vc14_runtime=14.40.33810
+  - vs2015_runtime=14.40.33810
+  - wheel=0.44.0
+  - xz=5.2.6
+  - pip:
+      - accelerate==0.31.0
+      - aiohappyeyeballs==2.4.0
+      - aiohttp==3.10.5
+      - aiosignal==1.3.1
+      - annotated-types==0.7.0
+      - annoy==1.17.3
+      - anyio==4.4.0
+      - argon2-cffi==23.1.0
+      - argon2-cffi-bindings==21.2.0
+      - arrow==1.3.0
+      - asttokens==2.4.1
+      - async-lru==2.0.4
+      - async-timeout==4.0.3
+      - attrs==24.2.0
+      - babel==2.16.0
+      - beautifulsoup4==4.12.3
+      - bertopic==0.16.3
+      - bitsandbytes==0.43.1
+      - bleach==6.1.0
+      - boto3==1.35.15
+      - botocore==1.35.15
+      - certifi==2024.8.30
+      - cffi==1.17.1
+      - charset-normalizer==3.3.2
+      - click==8.1.7
+      - cloudpickle==3.0.0
+      - cohere==5.5.8
+      - colorama==0.4.6
+      - colorcet==3.1.0
+      - colorspacious==1.1.2
+      - comm==0.2.2
+      - contourpy==1.3.0
+      - cycler==0.12.1
+      - dask==2024.8.2
+      - dataclasses-json==0.6.7
+      - datamapplot==0.3.0
+      - datasets==2.20.0
+      - datashader==0.16.3
+      - debugpy==1.8.5
+      - decorator==5.1.1
+      - defusedxml==0.7.1
+      - dill==0.3.8
+      - diskcache==5.6.3
+      - distro==1.9.0
+      - docstring-parser==0.16
+      - duckduckgo-search==6.1.6
+      - eval-type-backport==0.2.0
+      - evaluate==0.4.2
+      - exceptiongroup==1.2.2
+      - executing==2.1.0
+      - fastavro==1.9.7
+      - fastjsonschema==2.20.0
+      - filelock==3.16.0
+      - fonttools==4.53.1
+      - fqdn==1.5.1
+      - frozenlist==1.4.1
+      - fsspec==2024.5.0
+      - gensim==4.3.2
+      - greenlet==3.0.3
+      - h11==0.14.0
+      - hdbscan==0.8.38.post1
+      - httpcore==1.0.5
+      - httpx==0.27.2
+      - httpx-sse==0.4.0
+      - huggingface-hub==0.24.6
+      - idna==3.8
+      - imageio==2.35.1
+      - importlib-metadata==8.4.0
+      - intel-openmp==2021.4.0
+      - ipykernel==6.29.5
+      - ipython==8.27.0
+      - ipywidgets==8.1.3
+      - isoduration==20.11.0
+      - jedi==0.19.1
+      - jinja2==3.1.4
+      - jmespath==1.0.1
+      - joblib==1.4.2
+      - json5==0.9.25
+      - jsonpatch==1.33
+      - jsonpointer==3.0.0
+      - jsonschema==4.23.0
+      - jsonschema-specifications==2023.12.1
+      - jupyter-client==8.6.2
+      - jupyter-core==5.7.2
+      - jupyter-events==0.10.0
+      - jupyter-lsp==2.2.5
+      - jupyter-server==2.14.2
+      - jupyter-server-terminals==0.5.3
+      - jupyterlab==4.2.2
+      - jupyterlab-pygments==0.3.0
+      - jupyterlab-server==2.27.3
+      - jupyterlab-widgets==3.0.13
+      - kiwisolver==1.4.7
+      - langchain==0.2.5
+      - langchain-community==0.2.5
+      - langchain-core==0.2.38
+      - langchain-openai==0.1.8
+      - langchain-text-splitters==0.2.4
+      - langsmith==0.1.117
+      - lazy-loader==0.4
+      - llama-cpp-python==0.2.78
+      - llvmlite==0.43.0
+      - locket==1.0.0
+      - markdown-it-py==3.0.0
+      - markupsafe==2.1.5
+      - marshmallow==3.22.0
+      - matplotlib==3.9.0
+      - matplotlib-inline==0.1.7
+      - mdurl==0.1.2
+      - mistune==3.0.2
+      - mkl==2021.4.0
+      - mpmath==1.3.0
+      - mteb==1.12.39
+      - multidict==6.1.0
+      - multipledispatch==1.0.0
+      - multiprocess==0.70.16
+      - mypy-extensions==1.0.0
+      - nbclient==0.10.0
+      - nbconvert==7.16.4
+      - nbformat==5.10.4
+      - nest-asyncio==1.6.0
+      - networkx==3.3
+      - nltk==3.8.1
+      - notebook-shim==0.2.4
+      - numba==0.60.0
+      - numexpr==2.10.0
+      - numpy==1.26.4
+      - openai==1.34.0
+      - orjson==3.10.7
+      - overrides==7.7.0
+      - packaging==24.1
+      - pandas==2.2.2
+      - pandocfilters==1.5.1
+      - param==2.1.1
+      - parameterized==0.9.0
+      - parso==0.8.4
+      - partd==1.4.2
+      - peft==0.11.1
+      - pillow==10.4.0
+      - platformdirs==4.3.2
+      - plotly==5.24.0
+      - polars==1.6.0
+      - prometheus-client==0.20.0
+      - prompt-toolkit==3.0.47
+      - psutil==6.0.0
+      - pure-eval==0.2.3
+      - pyarrow==17.0.0
+      - pyarrow-hotfix==0.6
+      - pycparser==2.22
+      - pyct==0.5.0
+      - pydantic==2.9.1
+      - pydantic-core==2.23.3
+      - pygments==2.18.0
+      - pylabeladjust==0.1.13
+      - pynndescent==0.5.13
+      - pyparsing==3.1.4
+      - pyqtree==1.0.0
+      - pyreqwest-impersonate==0.5.3
+      - python-dateutil==2.9.0.post0
+      - python-json-logger==2.0.7
+      - pytrec-eval-terrier==0.5.6
+      - pytz==2024.1
+      - pywin32==306
+      - pywinpty==2.0.13
+      - pyyaml==6.0.2
+      - pyzmq==26.2.0
+      - referencing==0.35.1
+      - regex==2024.7.24
+      - requests==2.32.3
+      - rfc3339-validator==0.1.4
+      - rfc3986-validator==0.1.1
+      - rich==13.8.1
+      - rpds-py==0.20.0
+      - s3transfer==0.10.2
+      - safetensors==0.4.5
+      - scikit-image==0.24.0
+      - scikit-learn==1.5.0
+      - send2trash==1.8.3
+      - sentence-transformers==3.0.1
+      - sentencepiece==0.2.0
+      - seqeval==1.2.2
+      - setfit==1.0.3
+      - shtab==1.7.1
+      - six==1.16.0
+      - smart-open==7.0.4
+      - sniffio==1.3.1
+      - soupsieve==2.6
+      - sqlalchemy==2.0.34
+      - stack-data==0.6.3
+      - sympy==1.13.2
+      - tbb==2021.13.1
+      - tenacity==8.5.0
+      - terminado==0.18.1
+      - threadpoolctl==3.5.0
+      - tifffile==2024.8.30
+      - tiktoken==0.7.0
+      - tinycss2==1.3.0
+      - tokenizers==0.19.1
+      - tomli==2.0.1
+      - toolz==0.12.1
+      - torch==2.3.1
+      - tornado==6.4.1
+      - tqdm==4.66.5
+      - traitlets==5.14.3
+      - transformers==4.41.2
+      - trl==0.9.4
+      - types-python-dateutil==2.9.0.20240906
+      - types-requests==2.32.0.20240907
+      - typing-extensions==4.12.2
+      - typing-inspect==0.9.0
+      - tyro==0.8.10
+      - tzdata==2024.1
+      - umap-learn==0.5.6
+      - uri-template==1.3.0
+      - urllib3==2.2.2
+      - wcwidth==0.2.13
+      - webcolors==24.8.0
+      - webencodings==0.5.1
+      - websocket-client==1.8.0
+      - widgetsnbextension==4.0.13
+      - wrapt==1.16.0
+      - xarray==2024.7.0
+      - xxhash==3.5.0
+      - yarl==1.11.1
+      - zipp==3.20.1
+prefix: C:\ProgramData\miniconda3\envs\thellmbook

requirements.txt

@@ -0,0 +1,43 @@
+# Data handling
+numpy == 1.26.4
+pandas == 2.2.2
+datasets == 2.20.0
+
+# Environment
+jupyterlab == 4.2.2
+ipywidgets == 8.1.3
+
+# Hard dependencies throughout the entire book
+torch == 2.3.1
+transformers == 4.41.2
+sentence-transformers == 3.0.1
+matplotlib == 3.9.0
+scikit-learn == 1.5.0
+sentencepiece == 0.2.0
+nltk == 3.8.1
+evaluate == 0.4.2
+scipy == 1.12.0  # TEMPORARY DEP BECAUSE OF https://github.com/piskvorky/gensim/issues/3525
+
+# Cloud providers
+openai == 1.34.0
+cohere == 5.5.8
+
+# Chapter-specific dependencies
+datamapplot == 0.3.0
+faiss-cpu==1.8.0
+bertopic == 0.16.3
+annoy == 1.17.3
+llama_cpp_python == 0.2.78 -C cmake.args="-DLLAMA_BLAS=ON"
+numexpr == 2.10.0
+langchain == 0.2.5
+langchain-community == 0.2.5
+langchain-openai==0.1.8
+duckduckgo-search == 6.1.6
+gensim == 4.3.2
+setfit == 1.0.3
+seqeval == 1.2.2
+trl == 0.9.4
+peft == 0.11.1
+accelerate == 0.31.0
+bitsandbytes == 0.43.1
+mteb == 1.12.39

requirements_min.txt

@@ -0,0 +1,43 @@
+# Data handling
+numpy >= 1.26.4
+pandas >= 2.2.2
+datasets >= 2.20.0
+
+# Environment
+jupyterlab >= 4.2.2
+ipywidgets >= 8.1.3
+
+# Hard dependencies throughout the entire book
+torch >= 2.3.1
+transformers >= 4.41.2
+sentence-transformers >= 3.0.1
+matplotlib >= 3.9.0
+scikit-learn >= 1.5.0
+sentencepiece >= 0.2.0
+nltk >= 3.8.1
+evaluate >= 0.4.2
+scipy == 1.12.0  # TEMPORARY DEP BECAUSE OF https://github.com/piskvorky/gensim/issues/3525
+
+# Cloud providers
+openai >= 1.34.0
+cohere >= 5.5.8
+
+# Chapter-specific dependencies
+datamapplot >= 0.3.0
+faiss-cpu >= 1.8.0
+bertopic >= 0.16.3       
+annoy >= 1.17.3              
+llama_cpp_python >= 0.2.78 -C cmake.args="-DLLAMA_BLAS=ON"
+numexpr >= 2.10.0
+langchain >= 0.2.5
+langchain-community >= 0.2.5
+langchain-openai >= 0.1.8
+duckduckgo-search >= 6.1.6
+gensim >= 4.3.2             
+setfit >= 1.0.3              
+seqeval >= 1.2.2           
+trl >= 0.9.4                
+peft >= 0.11.1               
+accelerate >= 0.31.0       
+bitsandbytes >= 0.43.1       
+mteb >= 1.12.39