tensorblock/kamelcharaf_grpo-meta-3.1-8b-meta-3.1-8b-mrd3-s7-sum_token_prompt-merged-gguf overview

{
  "metadata": {},
  "card_data": {
    "library_name": "transformers",
    "tags": [
      "TensorBlock",
      "GGUF"
    ],
    "base_model": "kamelcharaf/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged",
    "frontmatter": {
      "library_name": "transformers",
      "tags": [
        "TensorBlock",
        "GGUF"
      ],
      "base_model": "kamelcharaf/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged"
    },
    "hero_image_url": "https://i.imgur.com/jC7kdl8.jpeg",
    "summary": "![Website](https://tensorblock.co) ![Twitter](https://twitter.com/tensorblock_aoi) ![Discord](https://discord.gg/Ej5NmeHFf2) ![GitHub](https://github.com/TensorBlock) ![Telegram](https://t.me/TensorBlock)",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlibrary_name: transformers\ntags:\n- TensorBlock\n- GGUF\nbase_model: kamelcharaf/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged\n---\n\n<div style=\"width: auto; margin-left: auto; margin-right: auto\">\n<img src=\"https://i.imgur.com/jC7kdl8.jpeg\" alt=\"TensorBlock\" style=\"width: 100%; min-width: 400px; display: block; margin: auto;\">\n</div>\n\n[![Website](https://img.shields.io/badge/Website-tensorblock.co-blue?logo=google-chrome&logoColor=white)](https://tensorblock.co)\n[![Twitter](https://img.shields.io/twitter/follow/tensorblock_aoi?style=social)](https://twitter.com/tensorblock_aoi)\n[![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white)](https://discord.gg/Ej5NmeHFf2)\n[![GitHub](https://img.shields.io/badge/GitHub-TensorBlock-black?logo=github&logoColor=white)](https://github.com/TensorBlock)\n[![Telegram](https://img.shields.io/badge/Telegram-Group-blue?logo=telegram)](https://t.me/TensorBlock)\n\n\n## kamelcharaf/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged - GGUF\n\n<div style=\"text-align: left; margin: 20px 0;\">\n    <a href=\"https://discord.com/invite/Ej5NmeHFf2\" style=\"display: inline-block; padding: 10px 20px; background-color: #5865F2; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;\">\n        Join our Discord to learn more about what we're building ↗\n    </a>\n</div>\n\nThis repo contains GGUF format model files for [kamelcharaf/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged](https://huggingface.co/kamelcharaf/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged).\n\nThe files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5753](https://github.com/ggml-org/llama.cpp/commit/73e53dc834c0a2336cd104473af6897197b96277).\n\n## Our projects\n<table border=\"1\" cellspacing=\"0\" cellpadding=\"10\">\n  <tr>\n    <th colspan=\"2\" style=\"font-size: 25px;\">Forge</th>\n  </tr>\n  <tr>\n    <th colspan=\"2\">\n      <img src=\"https://imgur.com/faI5UKh.jpeg\" alt=\"Forge Project\" width=\"900\"/>\n    </th>\n  </tr>\n  <tr>\n    <th colspan=\"2\">An OpenAI-compatible multi-provider routing layer.</th>\n  </tr>\n  <tr>\n    <th colspan=\"2\">\n      <a href=\"https://github.com/TensorBlock/forge\" target=\"_blank\" style=\"\n        display: inline-block;\n        padding: 8px 16px;\n        background-color: #FF7F50;\n        color: white;\n        text-decoration: none;\n        border-radius: 6px;\n        font-weight: bold;\n        font-family: sans-serif;\n      \">🚀 Try it now! 🚀</a>\n    </th>\n  </tr>\n\n  <tr>\n    <th style=\"font-size: 25px;\">Awesome MCP Servers</th>\n    <th style=\"font-size: 25px;\">TensorBlock Studio</th>\n  </tr>\n  <tr>\n    <th><img src=\"https://imgur.com/2Xov7B7.jpeg\" alt=\"MCP Servers\" width=\"450\"/></th>\n    <th><img src=\"https://imgur.com/pJcmF5u.jpeg\" alt=\"Studio\" width=\"450\"/></th>\n  </tr>\n  <tr>\n    <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>\n    <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>\n  </tr>\n  <tr>\n    <th>\n      <a href=\"https://github.com/TensorBlock/awesome-mcp-servers\" target=\"_blank\" style=\"\n        display: inline-block;\n        padding: 8px 16px;\n        background-color: #FF7F50;\n        color: white;\n        text-decoration: none;\n        border-radius: 6px;\n        font-weight: bold;\n        font-family: sans-serif;\n      \">👀 See what we built 👀</a>\n    </th>\n    <th>\n      <a href=\"https://github.com/TensorBlock/TensorBlock-Studio\" target=\"_blank\" style=\"\n        display: inline-block;\n        padding: 8px 16px;\n        background-color: #FF7F50;\n        color: white;\n        text-decoration: none;\n        border-radius: 6px;\n        font-weight: bold;\n        font-family: sans-serif;\n      \">👀 See what we built 👀</a>\n    </th>\n  </tr>\n</table>\n\n## Prompt template\n\n```\n<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n```\n\n## Model file specification\n\n| Filename | Quant type | File Size | Description |\n| -------- | ---------- | --------- | ----------- |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q2_K.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q3_K_S.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q3_K_S.gguf) | Q3_K_S | 3.664 GB | very small, high quality loss |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q3_K_M.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q3_K_L.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q4_0.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q4_K_S.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q4_K_M.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q5_0.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q5_K_S.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q5_K_M.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q6_K.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |\n| [GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q8_0.gguf](https://huggingface.co/tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF/blob/main/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |\n\n\n## Downloading instruction\n\n### Command line\n\nFirstly, install Huggingface Client\n\n```shell\npip install -U \"huggingface_hub[cli]\"\n```\n\nThen, downoad the individual model file the a local directory\n\n```shell\nhuggingface-cli download tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF --include \"GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-Q2_K.gguf\" --local-dir MY_LOCAL_DIR\n```\n\nIf you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:\n\n```shell\nhuggingface-cli download tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'\n```\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "TensorBlock",
    "GGUF",
    "base_model:kamelcharaf/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged",
    "base_model:quantized:kamelcharaf/GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 85,
  "gated": false,
  "private": false,
  "last_modified": "2026-01-27T20:08:23.000Z",
  "created_at": "2025-06-30T19:00:26.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "6862deca1278efd9aaa18675",
  "id": "tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF",
  "modelId": "tensorblock/kamelcharaf_GRPO-meta-3.1-8B-meta-3.1-8B-mrd3-s7-sum_token_prompt-merged-GGUF",
  "sha": "a8213c8ad18a00e5f0af652529bd0de89703803a",
  "createdAt": "2025-06-30T19:00:26.000Z",
  "lastModified": "2026-01-27T20:08:23.000Z",
  "author": "tensorblock",
  "downloads": 85,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 3
}