richarderkhov/embeddedllm_-_mistral-7b-merge-14-v0.5-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Due to mlabonne/NeuralMarcoro14-7B updating its license to CC-BY-NC, our license will follow suit. # Model Description This is an experiment to test merging 14 models using DARE TIES 🦙 1. We first merge 14 models to produce EmbeddedLLM/Mistral-7B-Merge-14-v0.3. 2. The model is merged again using DARE TIES with:",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nMistral-7B-Merge-14-v0.5 - GGUF\n- Model creator: https://huggingface.co/EmbeddedLLM/\n- Original model: https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.5/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Mistral-7B-Merge-14-v0.5.Q2_K.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q2_K.gguf) | Q2_K | 2.53GB |\n| [Mistral-7B-Merge-14-v0.5.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [Mistral-7B-Merge-14-v0.5.IQ3_S.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [Mistral-7B-Merge-14-v0.5.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [Mistral-7B-Merge-14-v0.5.IQ3_M.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [Mistral-7B-Merge-14-v0.5.Q3_K.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q3_K.gguf) | Q3_K | 3.28GB |\n| [Mistral-7B-Merge-14-v0.5.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [Mistral-7B-Merge-14-v0.5.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [Mistral-7B-Merge-14-v0.5.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [Mistral-7B-Merge-14-v0.5.Q4_0.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [Mistral-7B-Merge-14-v0.5.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [Mistral-7B-Merge-14-v0.5.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [Mistral-7B-Merge-14-v0.5.Q4_K.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q4_K.gguf) | Q4_K | 4.07GB |\n| [Mistral-7B-Merge-14-v0.5.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [Mistral-7B-Merge-14-v0.5.Q4_1.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [Mistral-7B-Merge-14-v0.5.Q5_0.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [Mistral-7B-Merge-14-v0.5.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [Mistral-7B-Merge-14-v0.5.Q5_K.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q5_K.gguf) | Q5_K | 4.78GB |\n| [Mistral-7B-Merge-14-v0.5.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [Mistral-7B-Merge-14-v0.5.Q5_1.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [Mistral-7B-Merge-14-v0.5.Q6_K.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q6_K.gguf) | Q6_K | 5.53GB |\n| [Mistral-7B-Merge-14-v0.5.Q8_0.gguf](https://huggingface.co/RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf/blob/main/Mistral-7B-Merge-14-v0.5.Q8_0.gguf) | Q8_0 | 7.17GB |\n\n\n\n\nOriginal model description:\n---\nlicense: cc-by-nc-4.0\nlanguage:\n- en\ntags:\n- merge\nbase_model:\n- EmbeddedLLM/Mistral-7B-Merge-14-v0.3\n- Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp\n- openchat/openchat-3.5-0106\n- mlabonne/NeuralMarcoro14-7B\n---\n\n# Update 2024-01-21\n\nDue to [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) updating its license to CC-BY-NC, our license will follow suit.\n\n# Model Description\n\nThis is an experiment to test merging 14 models using DARE TIES 🦙\n\n1. We first merge 14 models to produce [EmbeddedLLM/Mistral-7B-Merge-14-v0.3](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.3).\n2. The model is merged again using DARE TIES with:\n   - [Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp](https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp)\n   - [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)\n   - [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B)\n\n## Open LLM Leaderboard\n\n| Average    | 71.96 |\n|------------|-------|\n| ARC        | 68.69 |\n| HellaSwag  | 86.45 |\n| MMLU       | 65.65 |\n| TruthfulQA | 59.12 |\n| Winogrande | 80.66 |\n| GSM8K      | 71.19  |\n\n## Chat Template\n\nEither ChatML or Llama-2 chat template.\n\n## Merge Configuration\n\nThe merge config file for this model is here:\n\n```yaml\nmodels:\n  - model: mistralai/Mistral-7B-v0.1\n    # no parameters necessary for base model\n  - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.3\n    parameters:\n      weight: 0.3\n      density: 0.5\n  - model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp\n    parameters:\n      weight: 0.2\n      density: 0.5\n  - model: openchat/openchat-3.5-0106\n    parameters:\n      weight: 0.2\n      density: 0.5\n  - model: mlabonne/NeuralMarcoro14-7B\n    parameters:\n      weight: 0.3\n      density: 0.5\nmerge_method: dare_ties\nbase_model: mistralai/Mistral-7B-v0.1\n\nparameters:\n  int8_mask: true\ntokenizer_source: union\ndtype: bfloat16\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 177,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-04T07:24:30.000Z",
  "created_at": "2024-07-04T05:18:17.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "668630991af627989fd3c1ab",
  "id": "RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf",
  "modelId": "RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.5-gguf",
  "sha": "d7fae666c09363a79087f56c66213b88005aa01c",
  "createdAt": "2024-07-04T05:18:17.000Z",
  "lastModified": "2024-07-04T07:24:30.000Z",
  "author": "RichardErkhov",
  "downloads": 177,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}