mradermacher/codestral-21b-pruned-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "TroyDoesAI/Codestral-21B-Pruned",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "quantized_by": "mradermacher",
    "tags": [
      "rag",
      "context obedient",
      "TroyDoesAI",
      "Mermaid",
      "Flow",
      "Diagram",
      "Sequence",
      "Map",
      "Context",
      "Accurate",
      "Summarization",
      "Story",
      "Code",
      "Coder",
      "Architecture",
      "Retrieval",
      "Augmented",
      "Generation",
      "AI",
      "LLM",
      "Mistral",
      "LLama",
      "Large Language Model",
      "Retrieval Augmented Generation",
      "Troy Andrew Schultz",
      "LookingForWork",
      "OpenForHire",
      "IdoCoolStuff",
      "Knowledge Graph",
      "Knowledge",
      "Graph",
      "Accelerator",
      "Enthusiast",
      "Chatbot",
      "Personal Assistant",
      "Copilot",
      "lol",
      "tags",
      "Pruned",
      "efficient",
      "smaller",
      "small",
      "local",
      "open",
      "source",
      "open source",
      "quant",
      "quantize",
      "ablated",
      "Ablation",
      "uncensored ",
      "unaligned",
      "bad ",
      "alignment"
    ],
    "frontmatter": {
      "base_model": "TroyDoesAI/Codestral-21B-Pruned",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "quantized_by": "mradermacher",
      "tags": [
        "rag",
        "context obedient",
        "TroyDoesAI",
        "Mermaid",
        "Flow",
        "Diagram",
        "Sequence",
        "Map",
        "Context",
        "Accurate",
        "Summarization",
        "Story",
        "Code",
        "Coder",
        "Architecture",
        "Retrieval",
        "Augmented",
        "Generation",
        "AI",
        "LLM",
        "Mistral",
        "LLama",
        "Large Language Model",
        "Retrieval Augmented Generation",
        "Troy Andrew Schultz",
        "LookingForWork",
        "OpenForHire",
        "IdoCoolStuff",
        "Knowledge Graph",
        "Knowledge",
        "Graph",
        "Accelerator",
        "Enthusiast",
        "Chatbot",
        "Personal Assistant",
        "Copilot",
        "lol",
        "tags",
        "Pruned",
        "efficient",
        "smaller",
        "small",
        "local",
        "open",
        "source",
        "open source",
        "quant",
        "quantize",
        "ablated",
        "Ablation",
        "'uncensored '",
        "unaligned",
        "'bad '",
        "alignment"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      static quants of https://huggingface.co/TroyDoesAI/Codestral-21B-Pruned  weighted/imatrix quants are available at https://huggingface.co/mradermacher/Codestral-21B-Pruned-i1-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: TroyDoesAI/Codestral-21B-Pruned\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nquantized_by: mradermacher\ntags:\n- rag\n- context obedient\n- TroyDoesAI\n- Mermaid\n- Flow\n- Diagram\n- Sequence\n- Map\n- Context\n- Accurate\n- Summarization\n- Story\n- Code\n- Coder\n- Architecture\n- Retrieval\n- Augmented\n- Generation\n- AI\n- LLM\n- Mistral\n- LLama\n- Large Language Model\n- Retrieval Augmented Generation\n- Troy Andrew Schultz\n- LookingForWork\n- OpenForHire\n- IdoCoolStuff\n- Knowledge Graph\n- Knowledge\n- Graph\n- Accelerator\n- Enthusiast\n- Chatbot\n- Personal Assistant\n- Copilot\n- lol\n- tags\n- Pruned\n- efficient\n- smaller\n- small\n- local\n- open\n- source\n- open source\n- quant\n- quantize\n- ablated\n- Ablation\n- 'uncensored '\n- unaligned\n- 'bad '\n- alignment\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags:  -->\nstatic quants of https://huggingface.co/TroyDoesAI/Codestral-21B-Pruned\n\n<!-- provided-files -->\nweighted/imatrix quants are available at https://huggingface.co/mradermacher/Codestral-21B-Pruned-i1-GGUF\n## Usage\n\nIf you are unsure how to use GGUF files, refer to one of [TheBloke's\nREADMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for\nmore details, including on how to concatenate multi-part files.\n\n## Provided Quants\n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\n| Link | Type | Size/GB | Notes |\n|:-----|:-----|--------:|:------|\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.Q2_K.gguf) | Q2_K | 8.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.IQ3_XS.gguf) | IQ3_XS | 9.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.Q3_K_S.gguf) | Q3_K_S | 9.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.IQ3_S.gguf) | IQ3_S | 9.5 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.IQ3_M.gguf) | IQ3_M | 9.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.Q3_K_M.gguf) | Q3_K_M | 10.5 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.Q3_K_L.gguf) | Q3_K_L | 11.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.IQ4_XS.gguf) | IQ4_XS | 11.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.Q4_K_S.gguf) | Q4_K_S | 12.3 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.Q4_K_M.gguf) | Q4_K_M | 12.9 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.Q5_K_S.gguf) | Q5_K_S | 14.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.Q5_K_M.gguf) | Q5_K_M | 15.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.Q6_K.gguf) | Q6_K | 17.7 | very good quality |\n| [GGUF](https://huggingface.co/mradermacher/Codestral-21B-Pruned-GGUF/resolve/main/Codestral-21B-Pruned.Q8_0.gguf) | Q8_0 | 22.9 | fast, best quality |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)\n\nAnd here are Artefact2's thoughts on the matter:\nhttps://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n\n## FAQ / Model Request\n\nSee https://huggingface.co/mradermacher/model_requests for some answers to\nquestions you might have and/or if you want some other model quantized.\n\n## Thanks\n\nI thank my company, [nethype GmbH](https://www.nethype.de/), for letting\nme use its servers and providing upgrades to my workstation to enable\nthis work in my free time.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "rag",
    "context obedient",
    "TroyDoesAI",
    "Mermaid",
    "Flow",
    "Diagram",
    "Sequence",
    "Map",
    "Context",
    "Accurate",
    "Summarization",
    "Story",
    "Code",
    "Coder",
    "Architecture",
    "Retrieval",
    "Augmented",
    "Generation",
    "AI",
    "LLM",
    "Mistral",
    "LLama",
    "Large Language Model",
    "Retrieval Augmented Generation",
    "Troy Andrew Schultz",
    "LookingForWork",
    "OpenForHire",
    "IdoCoolStuff",
    "Knowledge Graph",
    "Knowledge",
    "Graph",
    "Accelerator",
    "Enthusiast",
    "Chatbot",
    "Personal Assistant",
    "Copilot",
    "lol",
    "tags",
    "Pruned",
    "efficient",
    "smaller",
    "small",
    "local",
    "open",
    "source",
    "open source",
    "quant",
    "quantize",
    "ablated",
    "Ablation",
    "uncensored ",
    "unaligned",
    "bad ",
    "alignment",
    "en",
    "base_model:TroyDoesAI/Codestral-21B-Pruned",
    "base_model:quantized:TroyDoesAI/Codestral-21B-Pruned",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 97,
  "gated": false,
  "private": false,
  "last_modified": "2024-06-01T15:17:13.000Z",
  "created_at": "2024-06-01T07:26:00.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "665acd085151e286e84bb623",
  "id": "mradermacher/Codestral-21B-Pruned-GGUF",
  "modelId": "mradermacher/Codestral-21B-Pruned-GGUF",
  "sha": "312f1b0616efafc2a10b5ca2aecc907a7b3d2cef",
  "createdAt": "2024-06-01T07:26:00.000Z",
  "lastModified": "2024-06-01T15:17:13.000Z",
  "author": "mradermacher",
  "downloads": 97,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 16
}