TheBloke/Python-Code-13B-GGUF

1---2base_model: ajibawa-2023/Python-Code-13B3datasets:4- ajibawa-2023/Python-Code-23k-ShareGPT5inference: false6language:7- en8license: cc-by-nc-nd-4.09model_creator: Feynman Innovations10model_name: Python Code 13B11model_type: llama12prompt_template: 'This is a conversation with your helpful AI assistant. AI assistant13  can generate Python Code along with necessary explanation.14 15 16  Context17 18  You are a helpful AI assistant.19 20 21  USER: {prompt}22 23  ASSISTANT:24 25  '26quantized_by: TheBloke27tags:28- code29---30<!-- markdownlint-disable MD041 -->31 32<!-- header start -->33<!-- 200823 -->34<div style="width: auto; margin-left: auto; margin-right: auto">35<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">36</div>37<div style="display: flex; justify-content: space-between; width: 100%;">38    <div style="display: flex; flex-direction: column; align-items: flex-start;">39        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>40    </div>41    <div style="display: flex; flex-direction: column; align-items: flex-end;">42        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>43    </div>44</div>45<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>46<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">47<!-- header end -->48 49# Python Code 13B - GGUF50- Model creator: [Feynman Innovations](https://huggingface.co/ajibawa-2023)51- Original model: [Python Code 13B](https://huggingface.co/ajibawa-2023/Python-Code-13B)52 53<!-- description start -->54## Description55 56This repo contains GGUF format model files for [Feynman Innovations's Python Code 13B](https://huggingface.co/ajibawa-2023/Python-Code-13B).57 58These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).59 60<!-- description end -->61<!-- README_GGUF.md-about-gguf start -->62### About GGUF63 64GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.65 66Here is an incomplete list of clients and libraries that are known to support GGUF:67 68* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.69* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.70* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.71* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.72* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.73* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.74* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.75* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.76* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.77 78<!-- README_GGUF.md-about-gguf end -->79<!-- repositories-available start -->80## Repositories available81 82* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Python-Code-13B-AWQ)83* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Python-Code-13B-GPTQ)84* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Python-Code-13B-GGUF)85* [Feynman Innovations's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ajibawa-2023/Python-Code-13B)86<!-- repositories-available end -->87 88<!-- prompt-template start -->89## Prompt template: Ajibawa-Python-Code90 91```92This is a conversation with your helpful AI assistant. AI assistant can generate Python Code along with necessary explanation.93 94Context95You are a helpful AI assistant.96 97USER: {prompt}98ASSISTANT:99 100```101 102<!-- prompt-template end -->103<!-- licensing start -->104## Licensing105 106The creator of the source model has listed its license as `cc-by-nc-nd-4.0`, and this quantization has therefore used that same license.107 108As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.109 110In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Feynman Innovations's Python Code 13B](https://huggingface.co/ajibawa-2023/Python-Code-13B).111<!-- licensing end -->112<!-- compatibility_gguf start -->113## Compatibility114 115These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)116 117They are also compatible with many third party UIs and libraries - please see the list at the top of this README.118 119## Explanation of quantisation methods120 121<details>122  <summary>Click to see details</summary>123 124The new methods available are:125 126* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)127* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.128* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.129* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw130* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw131 132Refer to the Provided Files table below to see what files use which methods, and how.133</details>134<!-- compatibility_gguf end -->135 136<!-- README_GGUF.md-provided-files start -->137## Provided files138 139| Name | Quant method | Bits | Size | Max RAM required | Use case |140| ---- | ---- | ---- | ---- | ---- | ----- |141| [python-code-13b.Q2_K.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |142| [python-code-13b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |143| [python-code-13b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |144| [python-code-13b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |145| [python-code-13b.Q4_0.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |146| [python-code-13b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |147| [python-code-13b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |148| [python-code-13b.Q5_0.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |149| [python-code-13b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |150| [python-code-13b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |151| [python-code-13b.Q6_K.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |152| [python-code-13b.Q8_0.gguf](https://huggingface.co/TheBloke/Python-Code-13B-GGUF/blob/main/python-code-13b.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |153 154**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.155 156 157 158<!-- README_GGUF.md-provided-files end -->159 160<!-- README_GGUF.md-how-to-download start -->161## How to download GGUF files162 163**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.164 165The following clients/libraries will automatically download models for you, providing a list of available models to choose from:166 167* LM Studio168* LoLLMS Web UI169* Faraday.dev170 171### In `text-generation-webui`172 173Under Download Model, you can enter the model repo: TheBloke/Python-Code-13B-GGUF and below it, a specific filename to download, such as: python-code-13b.Q4_K_M.gguf.174 175Then click Download.176 177### On the command line, including multiple files at once178 179I recommend using the `huggingface-hub` Python library:180 181```shell182pip3 install huggingface-hub183```184 185Then you can download any individual model file to the current directory, at high speed, with a command like this:186 187```shell188huggingface-cli download TheBloke/Python-Code-13B-GGUF python-code-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False189```190 191<details>192  <summary>More advanced huggingface-cli download usage</summary>193 194You can also download multiple files at once with a pattern:195 196```shell197huggingface-cli download TheBloke/Python-Code-13B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'198```199 200For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).201 202To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:203 204```shell205pip3 install hf_transfer206```207 208And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:209 210```shell211HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Python-Code-13B-GGUF python-code-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False212```213 214Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.215</details>216<!-- README_GGUF.md-how-to-download end -->217 218<!-- README_GGUF.md-how-to-run start -->219## Example `llama.cpp` command220 221Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.222 223```shell224./main -ngl 32 -m python-code-13b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "This is a conversation with your helpful AI assistant. AI assistant can generate Python Code along with necessary explanation.\n\nContext\nYou are a helpful AI assistant.\n\nUSER: {prompt}\nASSISTANT:"225```226 227Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.228 229Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.230 231If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`232 233For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)234 235## How to run in `text-generation-webui`236 237Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).238 239## How to run from Python code240 241You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.242 243### How to load this model in Python code, using ctransformers244 245#### First install the package246 247Run one of the following commands, according to your system:248 249```shell250# Base ctransformers with no GPU acceleration251pip install ctransformers252# Or with CUDA GPU acceleration253pip install ctransformers[cuda]254# Or with AMD ROCm GPU acceleration (Linux only)255CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers256# Or with Metal GPU acceleration for macOS systems only257CT_METAL=1 pip install ctransformers --no-binary ctransformers258```259 260#### Simple ctransformers example code261 262```python263from ctransformers import AutoModelForCausalLM264 265# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.266llm = AutoModelForCausalLM.from_pretrained("TheBloke/Python-Code-13B-GGUF", model_file="python-code-13b.Q4_K_M.gguf", model_type="llama", gpu_layers=50)267 268print(llm("AI is going to"))269```270 271## How to use with LangChain272 273Here are guides on using llama-cpp-python and ctransformers with LangChain:274 275* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)276* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)277 278<!-- README_GGUF.md-how-to-run end -->279 280<!-- footer start -->281<!-- 200823 -->282## Discord283 284For further support, and discussions on these models and AI in general, join us at:285 286[TheBloke AI's Discord server](https://discord.gg/theblokeai)287 288## Thanks, and how to contribute289 290Thanks to the [chirper.ai](https://chirper.ai) team!291 292Thanks to Clay from [gpus.llm-utils.org](llm-utils)!293 294I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.295 296If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.297 298Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.299 300* Patreon: https://patreon.com/TheBlokeAI301* Ko-Fi: https://ko-fi.com/TheBlokeAI302 303**Special thanks to**: Aemon Algiz.304 305**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius306 307 308Thank you to all my generous patrons and donaters!309 310And thank you again to a16z for their generous grant.311 312<!-- footer end -->313 314<!-- original-model-card start -->315# Original model card: Feynman Innovations's Python Code 13B316 317 318**Python-Code-13B**319 320Large Language Models (LLMs) are good with code generations. Sometimes LLMs do make mistakes in code generation. How about if they can give detailed explanation along with the code.321This is what I have tried over here. The base Llama-2 model was used for training purpose. It is trained on around 23000+ set of codes. Each set having 2 conversations.322This data was generated using GPT-3.5, GPT-4 etc. This conversation is in Vicuna/ShareGPT format. Each set, along with code, has detailed explanation.323I have released the [data](https://huggingface.co/datasets/ajibawa-2023/Python-Code-23k-ShareGPT).324 325**Training:**326Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 13 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta.327 328 329**GPTQ GGML & AWQ**330 331GPTQ: TBA332 333GGUF: TBA334 335AWQ: TBA336 337 338**Example Prompt:**339```340This is a conversation with your helpful AI assistant. AI assistant can generate Python Code along with necessary explanation.341 342Context343You are a helpful AI assistant.344 345USER: <prompt>346ASSISTANT:347```348 349<!-- original-model-card end -->350