bartowski/dolphin-2.8-mistral-7b-v02-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "alpindale/Mistral-7B-v0.2-hf",
    "tags": [
      "generated_from_trainer"
    ],
    "model-index": [
      {
        "name": "workspace/dolphin-2.8-mistral-7b",
        "results": []
      }
    ],
    "quantized_by": "bartowski",
    "pipeline_tag": "text-generation",
    "frontmatter": {
      "base_model": "alpindale/Mistral-7B-v0.2-hf",
      "tags": [
        "generated_from_trainer",
        "name: workspace/dolphin-2.8-mistral-7b"
      ],
      "quantized_by": "bartowski",
      "pipeline_tag": "text-generation"
    },
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: alpindale/Mistral-7B-v0.2-hf\ntags:\n- generated_from_trainer\nmodel-index:\n- name: workspace/dolphin-2.8-mistral-7b\n  results: []\nquantized_by: bartowski\npipeline_tag: text-generation\n---\n\n## Llamacpp Quantizations of dolphin-2.8-mistral-7b-v02\n\nUsing <a href=\"https://github.com/ggerganov/llama.cpp/\">llama.cpp</a> release <a href=\"https://github.com/ggerganov/llama.cpp/releases/tag/b2536\">b2536</a> for quantization.\n\nOriginal model: https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02\n\nDownload a file (not the whole branch) from below:\n\n| Filename | Quant type | File Size | Description |\n| -------- | ---------- | --------- | ----------- |\n| [dolphin-2.8-mistral-7b-v02-Q8_0.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |\n| [dolphin-2.8-mistral-7b-v02-Q6_K.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |\n| [dolphin-2.8-mistral-7b-v02-Q5_K_M.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |\n| [dolphin-2.8-mistral-7b-v02-Q5_K_S.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |\n| [dolphin-2.8-mistral-7b-v02-Q5_0.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |\n| [dolphin-2.8-mistral-7b-v02-Q4_K_M.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, uses about 4.83 bits per weight. |\n| [dolphin-2.8-mistral-7b-v02-Q4_K_S.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |\n| [dolphin-2.8-mistral-7b-v02-IQ4_NL.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-IQ4_NL.gguf) | IQ4_NL | 4.15GB | Decent quality, similar to Q4_K_S, new method of quanting, |\n| [dolphin-2.8-mistral-7b-v02-IQ4_XS.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-IQ4_XS.gguf) | IQ4_XS | 3.94GB | Decent quality, new method with similar performance to Q4. |\n| [dolphin-2.8-mistral-7b-v02-Q4_0.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |\n| [dolphin-2.8-mistral-7b-v02-Q3_K_L.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |\n| [dolphin-2.8-mistral-7b-v02-Q3_K_M.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |\n| [dolphin-2.8-mistral-7b-v02-IQ3_M.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-IQ3_M.gguf) | IQ3_M | 3.28GB | Medium-low quality, new method with decent performance. |\n| [dolphin-2.8-mistral-7b-v02-IQ3_S.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-IQ3_S.gguf) | IQ3_S | 3.18GB | Lower quality, new method with decent performance, recommended over Q3 quants. |\n| [dolphin-2.8-mistral-7b-v02-Q3_K_S.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |\n| [dolphin-2.8-mistral-7b-v02-Q2_K.gguf](https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF/blob/main/dolphin-2.8-mistral-7b-v02-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.\n\nWant to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "generated_from_trainer",
    "text-generation",
    "base_model:mistral-community/Mistral-7B-v0.2",
    "base_model:quantized:mistral-community/Mistral-7B-v0.2",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 26,
  "downloads": 472,
  "gated": false,
  "private": false,
  "last_modified": "2024-03-29T03:39:33.000Z",
  "created_at": "2024-03-29T03:27:25.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "6606351db3d0e949eefa984c",
  "id": "bartowski/dolphin-2.8-mistral-7b-v02-GGUF",
  "modelId": "bartowski/dolphin-2.8-mistral-7b-v02-GGUF",
  "sha": "0efc2ef61bed1bfe1f57afcecdc2c93af3a1220b",
  "createdAt": "2024-03-29T03:27:25.000Z",
  "lastModified": "2024-03-29T03:39:33.000Z",
  "author": "bartowski",
  "downloads": 472,
  "likes": 26,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 18
}