tensorblock/generative-qa-model-GGUF
090
1---2license: mit3library_name: transformers4base_model: blapuma/generative-qa-model5tags:6- TensorBlock7- GGUF8---9 10<div style="width: auto; margin-left: auto; margin-right: auto">11<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">12</div>13 14[](https://tensorblock.co)15[](https://twitter.com/tensorblock_aoi)16[](https://discord.gg/Ej5NmeHFf2)17[](https://github.com/TensorBlock)18[](https://t.me/TensorBlock)19 20 21## blapuma/generative-qa-model - GGUF22 23This repo contains GGUF format model files for [blapuma/generative-qa-model](https://huggingface.co/blapuma/generative-qa-model).24 25The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).26 27 28## Our projects29<table border="1" cellspacing="0" cellpadding="10">30 <tr>31 <th colspan="2" style="font-size: 25px;">Forge</th>32 </tr>33 <tr>34 <th colspan="2">35 <img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>36 </th>37 </tr>38 <tr>39 <th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>40 </tr>41 <tr>42 <th colspan="2">43 <a href="https://github.com/TensorBlock/forge" target="_blank" style="44 display: inline-block;45 padding: 8px 16px;46 background-color: #FF7F50;47 color: white;48 text-decoration: none;49 border-radius: 6px;50 font-weight: bold;51 font-family: sans-serif;52 ">🚀 Try it now! 🚀</a>53 </th>54 </tr>55 56 <tr>57 <th style="font-size: 25px;">Awesome MCP Servers</th>58 <th style="font-size: 25px;">TensorBlock Studio</th>59 </tr>60 <tr>61 <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>62 <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>63 </tr>64 <tr>65 <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>66 <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>67 </tr>68 <tr>69 <th>70 <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="71 display: inline-block;72 padding: 8px 16px;73 background-color: #FF7F50;74 color: white;75 text-decoration: none;76 border-radius: 6px;77 font-weight: bold;78 font-family: sans-serif;79 ">👀 See what we built 👀</a>80 </th>81 <th>82 <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="83 display: inline-block;84 padding: 8px 16px;85 background-color: #FF7F50;86 color: white;87 text-decoration: none;88 border-radius: 6px;89 font-weight: bold;90 font-family: sans-serif;91 ">👀 See what we built 👀</a>92 </th>93 </tr>94</table>95## Prompt template96 97 98```99<s><|user|>100{prompt}<|end|>101<|assistant|>102```103 104## Model file specification105 106| Filename | Quant type | File Size | Description |107| -------- | ---------- | --------- | ----------- |108| [generative-qa-model-Q2_K.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q2_K.gguf) | Q2_K | 1.319 GB | smallest, significant quality loss - not recommended for most purposes |109| [generative-qa-model-Q3_K_S.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q3_K_S.gguf) | Q3_K_S | 1.566 GB | very small, high quality loss |110| [generative-qa-model-Q3_K_M.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q3_K_M.gguf) | Q3_K_M | 1.821 GB | very small, high quality loss |111| [generative-qa-model-Q3_K_L.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q3_K_L.gguf) | Q3_K_L | 1.944 GB | small, substantial quality loss |112| [generative-qa-model-Q4_0.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q4_0.gguf) | Q4_0 | 2.027 GB | legacy; small, very high quality loss - prefer using Q3_K_M |113| [generative-qa-model-Q4_K_S.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q4_K_S.gguf) | Q4_K_S | 2.038 GB | small, greater quality loss |114| [generative-qa-model-Q4_K_M.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q4_K_M.gguf) | Q4_K_M | 2.229 GB | medium, balanced quality - recommended |115| [generative-qa-model-Q5_0.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q5_0.gguf) | Q5_0 | 2.460 GB | legacy; medium, balanced quality - prefer using Q4_K_M |116| [generative-qa-model-Q5_K_S.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q5_K_S.gguf) | Q5_K_S | 2.460 GB | large, low quality loss - recommended |117| [generative-qa-model-Q5_K_M.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q5_K_M.gguf) | Q5_K_M | 2.622 GB | large, very low quality loss - recommended |118| [generative-qa-model-Q6_K.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q6_K.gguf) | Q6_K | 2.920 GB | very large, extremely low quality loss |119| [generative-qa-model-Q8_0.gguf](https://huggingface.co/tensorblock/generative-qa-model-GGUF/blob/main/generative-qa-model-Q8_0.gguf) | Q8_0 | 3.782 GB | very large, extremely low quality loss - not recommended |120 121 122## Downloading instruction123 124### Command line125 126Firstly, install Huggingface Client127 128```shell129pip install -U "huggingface_hub[cli]"130```131 132Then, downoad the individual model file the a local directory133 134```shell135huggingface-cli download tensorblock/generative-qa-model-GGUF --include "generative-qa-model-Q2_K.gguf" --local-dir MY_LOCAL_DIR136```137 138If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:139 140```shell141huggingface-cli download tensorblock/generative-qa-model-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'142```143