tensorblock/OpenCoder-1.5B-Instruct-GGUF
1195
1---2license: other3license_name: inf4license_link: https://huggingface.co/infly/OpenCoder-1.5B-Instruct/blob/main/LICENSE5language:6- en7- zh8base_model: infly/OpenCoder-1.5B-Instruct9pipeline_tag: text-generation10library_name: transformers11datasets:12- OpenCoder-LLM/opencoder-sft-stage113- OpenCoder-LLM/opencoder-sft-stage214tags:15- TensorBlock16- GGUF17---18 19<div style="width: auto; margin-left: auto; margin-right: auto">20<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">21</div>22 23[](https://tensorblock.co)24[](https://twitter.com/tensorblock_aoi)25[](https://discord.gg/Ej5NmeHFf2)26[](https://github.com/TensorBlock)27[](https://t.me/TensorBlock)28 29 30## infly/OpenCoder-1.5B-Instruct - GGUF31 32This repo contains GGUF format model files for [infly/OpenCoder-1.5B-Instruct](https://huggingface.co/infly/OpenCoder-1.5B-Instruct).33 34The 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).35 36## Our projects37<table border="1" cellspacing="0" cellpadding="10">38 <tr>39 <th colspan="2" style="font-size: 25px;">Forge</th>40 </tr>41 <tr>42 <th colspan="2">43 <img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>44 </th>45 </tr>46 <tr>47 <th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>48 </tr>49 <tr>50 <th colspan="2">51 <a href="https://github.com/TensorBlock/forge" target="_blank" style="52 display: inline-block;53 padding: 8px 16px;54 background-color: #FF7F50;55 color: white;56 text-decoration: none;57 border-radius: 6px;58 font-weight: bold;59 font-family: sans-serif;60 ">🚀 Try it now! 🚀</a>61 </th>62 </tr>63 64 <tr>65 <th style="font-size: 25px;">Awesome MCP Servers</th>66 <th style="font-size: 25px;">TensorBlock Studio</th>67 </tr>68 <tr>69 <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>70 <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>71 </tr>72 <tr>73 <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>74 <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>75 </tr>76 <tr>77 <th>78 <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="79 display: inline-block;80 padding: 8px 16px;81 background-color: #FF7F50;82 color: white;83 text-decoration: none;84 border-radius: 6px;85 font-weight: bold;86 font-family: sans-serif;87 ">👀 See what we built 👀</a>88 </th>89 <th>90 <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="91 display: inline-block;92 padding: 8px 16px;93 background-color: #FF7F50;94 color: white;95 text-decoration: none;96 border-radius: 6px;97 font-weight: bold;98 font-family: sans-serif;99 ">👀 See what we built 👀</a>100 </th>101 </tr>102</table>103## Prompt template104 105```106<|im_start|>system107{system_prompt}<|im_end|>108<|im_start|>user109{prompt}<|im_end|>110<|im_start|>assistant111```112 113## Model file specification114 115| Filename | Quant type | File Size | Description |116| -------- | ---------- | --------- | ----------- |117| [OpenCoder-1.5B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q2_K.gguf) | Q2_K | 1.139 GB | smallest, significant quality loss - not recommended for most purposes |118| [OpenCoder-1.5B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q3_K_S.gguf) | Q3_K_S | 1.139 GB | very small, high quality loss |119| [OpenCoder-1.5B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q3_K_M.gguf) | Q3_K_M | 1.215 GB | very small, high quality loss |120| [OpenCoder-1.5B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q3_K_L.gguf) | Q3_K_L | 1.269 GB | small, substantial quality loss |121| [OpenCoder-1.5B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q4_0.gguf) | Q4_0 | 1.183 GB | legacy; small, very high quality loss - prefer using Q3_K_M |122| [OpenCoder-1.5B-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q4_K_S.gguf) | Q4_K_S | 1.359 GB | small, greater quality loss |123| [OpenCoder-1.5B-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q4_K_M.gguf) | Q4_K_M | 1.418 GB | medium, balanced quality - recommended |124| [OpenCoder-1.5B-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q5_0.gguf) | Q5_0 | 1.394 GB | legacy; medium, balanced quality - prefer using Q4_K_M |125| [OpenCoder-1.5B-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q5_K_S.gguf) | Q5_K_S | 1.479 GB | large, low quality loss - recommended |126| [OpenCoder-1.5B-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q5_K_M.gguf) | Q5_K_M | 1.520 GB | large, very low quality loss - recommended |127| [OpenCoder-1.5B-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q6_K.gguf) | Q6_K | 1.947 GB | very large, extremely low quality loss |128| [OpenCoder-1.5B-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/OpenCoder-1.5B-Instruct-GGUF/blob/main/OpenCoder-1.5B-Instruct-Q8_0.gguf) | Q8_0 | 2.027 GB | very large, extremely low quality loss - not recommended |129 130 131## Downloading instruction132 133### Command line134 135Firstly, install Huggingface Client136 137```shell138pip install -U "huggingface_hub[cli]"139```140 141Then, downoad the individual model file the a local directory142 143```shell144huggingface-cli download tensorblock/OpenCoder-1.5B-Instruct-GGUF --include "OpenCoder-1.5B-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR145```146 147If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:148 149```shell150huggingface-cli download tensorblock/OpenCoder-1.5B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'151```152