tensorblock/code_gpt2_mini_model-GGUF

1---2license: apache-2.03datasets:4- HuggingFaceH4/ultrachat_200k5- mlabonne/CodeLlama-2-20k6- Intel/orca_dpo_pairs7language:8- en9pipeline_tag: text-generation10tags:11- gpt212- dpo13- TensorBlock14- GGUF15base_model: Sharathhebbar24/code_gpt2_mini_model16---17 18<div style="width: auto; margin-left: auto; margin-right: auto">19<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">20</div>21 22[![Website](https://img.shields.io/badge/Website-tensorblock.co-blue?logo=google-chrome&logoColor=white)](https://tensorblock.co)23[![Twitter](https://img.shields.io/twitter/follow/tensorblock_aoi?style=social)](https://twitter.com/tensorblock_aoi)24[![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white)](https://discord.gg/Ej5NmeHFf2)25[![GitHub](https://img.shields.io/badge/GitHub-TensorBlock-black?logo=github&logoColor=white)](https://github.com/TensorBlock)26[![Telegram](https://img.shields.io/badge/Telegram-Group-blue?logo=telegram)](https://t.me/TensorBlock)27 28 29## Sharathhebbar24/code_gpt2_mini_model - GGUF30 31This repo contains GGUF format model files for [Sharathhebbar24/code_gpt2_mini_model](https://huggingface.co/Sharathhebbar24/code_gpt2_mini_model).32 33The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).34 35## Our projects36<table border="1" cellspacing="0" cellpadding="10">37  <tr>38    <th colspan="2" style="font-size: 25px;">Forge</th>39  </tr>40  <tr>41    <th colspan="2">42      <img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>43    </th>44  </tr>45  <tr>46    <th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>47  </tr>48  <tr>49    <th colspan="2">50      <a href="https://github.com/TensorBlock/forge" target="_blank" style="51        display: inline-block;52        padding: 8px 16px;53        background-color: #FF7F50;54        color: white;55        text-decoration: none;56        border-radius: 6px;57        font-weight: bold;58        font-family: sans-serif;59      ">🚀 Try it now! 🚀</a>60    </th>61  </tr>62 63  <tr>64    <th style="font-size: 25px;">Awesome MCP Servers</th>65    <th style="font-size: 25px;">TensorBlock Studio</th>66  </tr>67  <tr>68    <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>69    <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>70  </tr>71  <tr>72    <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>73    <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>74  </tr>75  <tr>76    <th>77      <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="78        display: inline-block;79        padding: 8px 16px;80        background-color: #FF7F50;81        color: white;82        text-decoration: none;83        border-radius: 6px;84        font-weight: bold;85        font-family: sans-serif;86      ">👀 See what we built 👀</a>87    </th>88    <th>89      <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="90        display: inline-block;91        padding: 8px 16px;92        background-color: #FF7F50;93        color: white;94        text-decoration: none;95        border-radius: 6px;96        font-weight: bold;97        font-family: sans-serif;98      ">👀 See what we built 👀</a>99    </th>100  </tr>101</table>102## Prompt template103 104```105 106```107 108## Model file specification109 110| Filename | Quant type | File Size | Description |111| -------- | ---------- | --------- | ----------- |112| [code_gpt2_mini_model-Q2_K.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q2_K.gguf) | Q2_K | 0.081 GB | smallest, significant quality loss - not recommended for most purposes |113| [code_gpt2_mini_model-Q3_K_S.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q3_K_S.gguf) | Q3_K_S | 0.090 GB | very small, high quality loss |114| [code_gpt2_mini_model-Q3_K_M.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q3_K_M.gguf) | Q3_K_M | 0.098 GB | very small, high quality loss |115| [code_gpt2_mini_model-Q3_K_L.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q3_K_L.gguf) | Q3_K_L | 0.102 GB | small, substantial quality loss |116| [code_gpt2_mini_model-Q4_0.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q4_0.gguf) | Q4_0 | 0.107 GB | legacy; small, very high quality loss - prefer using Q3_K_M |117| [code_gpt2_mini_model-Q4_K_S.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q4_K_S.gguf) | Q4_K_S | 0.107 GB | small, greater quality loss |118| [code_gpt2_mini_model-Q4_K_M.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q4_K_M.gguf) | Q4_K_M | 0.113 GB | medium, balanced quality - recommended |119| [code_gpt2_mini_model-Q5_0.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q5_0.gguf) | Q5_0 | 0.122 GB | legacy; medium, balanced quality - prefer using Q4_K_M |120| [code_gpt2_mini_model-Q5_K_S.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q5_K_S.gguf) | Q5_K_S | 0.122 GB | large, low quality loss - recommended |121| [code_gpt2_mini_model-Q5_K_M.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q5_K_M.gguf) | Q5_K_M | 0.127 GB | large, very low quality loss - recommended |122| [code_gpt2_mini_model-Q6_K.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q6_K.gguf) | Q6_K | 0.138 GB | very large, extremely low quality loss |123| [code_gpt2_mini_model-Q8_0.gguf](https://huggingface.co/tensorblock/code_gpt2_mini_model-GGUF/blob/main/code_gpt2_mini_model-Q8_0.gguf) | Q8_0 | 0.178 GB | very large, extremely low quality loss - not recommended |124 125 126## Downloading instruction127 128### Command line129 130Firstly, install Huggingface Client131 132```shell133pip install -U "huggingface_hub[cli]"134```135 136Then, downoad the individual model file the a local directory137 138```shell139huggingface-cli download tensorblock/code_gpt2_mini_model-GGUF --include "code_gpt2_mini_model-Q2_K.gguf" --local-dir MY_LOCAL_DIR140```141 142If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:143 144```shell145huggingface-cli download tensorblock/code_gpt2_mini_model-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'146```147