richarderkhov/flozi00_-_mistral-7b-german-assistant-v4-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://www.primeline-solutions.com/skin/frontend/default/theme566/images/primeline-solutions-logo.png",
    "summary": "This model is an finetuned version for german instructions and conversations in style of Alpaca. \"### Assistant:\" \"### User:\", trained with a context length of 8k tokens. The dataset used is deduplicated and cleaned, with no codes inside and uncensored. The focus is on instruction following and conversational tasks. The model archictecture is based on Mistral v0.1 with 7B parameters, trained on 100% renewable energy powered hardware. This work is contributed by private research of flozi00",
    "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-german-assistant-v4 - GGUF\n- Model creator: https://huggingface.co/flozi00/\n- Original model: https://huggingface.co/flozi00/Mistral-7B-german-assistant-v4/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Mistral-7B-german-assistant-v4.Q2_K.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q2_K.gguf) | Q2_K | 2.53GB |\n| [Mistral-7B-german-assistant-v4.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [Mistral-7B-german-assistant-v4.IQ3_S.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [Mistral-7B-german-assistant-v4.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [Mistral-7B-german-assistant-v4.IQ3_M.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [Mistral-7B-german-assistant-v4.Q3_K.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q3_K.gguf) | Q3_K | 3.28GB |\n| [Mistral-7B-german-assistant-v4.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [Mistral-7B-german-assistant-v4.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [Mistral-7B-german-assistant-v4.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [Mistral-7B-german-assistant-v4.Q4_0.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [Mistral-7B-german-assistant-v4.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [Mistral-7B-german-assistant-v4.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [Mistral-7B-german-assistant-v4.Q4_K.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q4_K.gguf) | Q4_K | 4.07GB |\n| [Mistral-7B-german-assistant-v4.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [Mistral-7B-german-assistant-v4.Q4_1.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [Mistral-7B-german-assistant-v4.Q5_0.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [Mistral-7B-german-assistant-v4.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [Mistral-7B-german-assistant-v4.Q5_K.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q5_K.gguf) | Q5_K | 4.78GB |\n| [Mistral-7B-german-assistant-v4.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [Mistral-7B-german-assistant-v4.Q5_1.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [Mistral-7B-german-assistant-v4.Q6_K.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q6_K.gguf) | Q6_K | 3.56GB |\n| [Mistral-7B-german-assistant-v4.Q8_0.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf/blob/main/Mistral-7B-german-assistant-v4.Q8_0.gguf) | Q8_0 | 3.14GB |\n\n\n\n\nOriginal model description:\n---\ndatasets:\n- flozi00/conversations\nlanguage:\n- de\n---\n\n## This project is sponsored by [ ![PrimeLine](https://www.primeline-solutions.com/skin/frontend/default/theme566/images/primeline-solutions-logo.png) ](https://www.primeline-solutions.com/de/server/nach-einsatzzweck/gpu-rendering-hpc/)\n\n# Model Card\n\nThis model is an finetuned version for german instructions and conversations in style of Alpaca. \"### Assistant:\" \"### User:\", trained with a context length of 8k tokens.\nThe dataset used is deduplicated and cleaned, with no codes inside and uncensored. The focus is on instruction following and conversational tasks.\n\nThe model archictecture is based on Mistral v0.1 with 7B parameters, trained on 100% renewable energy powered hardware.\n\nThis work is contributed by private research of [flozi00](https://huggingface.co/flozi00)\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 811,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-31T05:43:10.000Z",
  "created_at": "2024-05-31T00:41:39.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66591cc32ec47299e797a297",
  "id": "RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf",
  "modelId": "RichardErkhov/flozi00_-_Mistral-7B-german-assistant-v4-gguf",
  "sha": "94db48987d7eb7afb68b3d0c3a78e17751e450a3",
  "createdAt": "2024-05-31T00:41:39.000Z",
  "lastModified": "2024-05-31T05:43:10.000Z",
  "author": "RichardErkhov",
  "downloads": 811,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}