richarderkhov/flozi00_-_llama-2-13b-german-assistant-v5-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:\" The dataset used is deduplicated and cleaned, with no codes inside. The focus is on instruction following and conversational tasks. The model archictecture is based on Llama version 2 with 13B parameters, trained on 100% renewable energy powered hardware. This work is contributed by private research of flozi00 Join discussions about german llm research, and plan larger training runs together: https://join.slack.com/t/slack-dtc7771/shared_invite/zt-219keplqu-hLwjm0xcFAOX7enERfBz0Q",
    "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\nLlama-2-13b-german-assistant-v5 - GGUF\n- Model creator: https://huggingface.co/flozi00/\n- Original model: https://huggingface.co/flozi00/Llama-2-13b-german-assistant-v5/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Llama-2-13b-german-assistant-v5.Q2_K.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q2_K.gguf) | Q2_K | 1.11GB |\n| [Llama-2-13b-german-assistant-v5.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q3_K_S.gguf) | Q3_K_S | 5.3GB |\n| [Llama-2-13b-german-assistant-v5.Q3_K.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q3_K.gguf) | Q3_K | 1.24GB |\n| [Llama-2-13b-german-assistant-v5.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q3_K_M.gguf) | Q3_K_M | 5.94GB |\n| [Llama-2-13b-german-assistant-v5.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q3_K_L.gguf) | Q3_K_L | 5.41GB |\n| [Llama-2-13b-german-assistant-v5.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.IQ4_XS.gguf) | IQ4_XS | 6.57GB |\n| [Llama-2-13b-german-assistant-v5.Q4_0.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q4_0.gguf) | Q4_0 | 6.9GB |\n| [Llama-2-13b-german-assistant-v5.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.IQ4_NL.gguf) | IQ4_NL | 6.94GB |\n| [Llama-2-13b-german-assistant-v5.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q4_K_S.gguf) | Q4_K_S | 6.95GB |\n| [Llama-2-13b-german-assistant-v5.Q4_K.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q4_K.gguf) | Q4_K | 7.36GB |\n| [Llama-2-13b-german-assistant-v5.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q4_K_M.gguf) | Q4_K_M | 7.36GB |\n| [Llama-2-13b-german-assistant-v5.Q4_1.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q4_1.gguf) | Q4_1 | 7.65GB |\n| [Llama-2-13b-german-assistant-v5.Q5_0.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q5_0.gguf) | Q5_0 | 8.4GB |\n| [Llama-2-13b-german-assistant-v5.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q5_K_S.gguf) | Q5_K_S | 8.4GB |\n| [Llama-2-13b-german-assistant-v5.Q5_K.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q5_K.gguf) | Q5_K | 8.64GB |\n| [Llama-2-13b-german-assistant-v5.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q5_K_M.gguf) | Q5_K_M | 8.64GB |\n| [Llama-2-13b-german-assistant-v5.Q5_1.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q5_1.gguf) | Q5_1 | 9.15GB |\n| [Llama-2-13b-german-assistant-v5.Q6_K.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q6_K.gguf) | Q6_K | 9.99GB |\n| [Llama-2-13b-german-assistant-v5.Q8_0.gguf](https://huggingface.co/RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf/blob/main/Llama-2-13b-german-assistant-v5.Q8_0.gguf) | Q8_0 | 12.94GB |\n\n\n\n\nOriginal model description:\n---\ndatasets:\n- flozi00/conversations\nlanguage:\n- en\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:\"\nThe dataset used is deduplicated and cleaned, with no codes inside. The focus is on instruction following and conversational tasks.\n\nThe model archictecture is based on Llama version 2 with 13B parameters, trained on 100% renewable energy powered hardware.\n\nThis work is contributed by private research of [flozi00](https://huggingface.co/flozi00)\n\n\nJoin discussions about german llm research, and plan larger training runs together: https://join.slack.com/t/slack-dtc7771/shared_invite/zt-219keplqu-hLwjm0xcFAOX7enERfBz0Q\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 376,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-31T04:15:20.000Z",
  "created_at": "2024-10-31T00:47:04.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6722d3888d90b18e4404dde1",
  "id": "RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf",
  "modelId": "RichardErkhov/flozi00_-_Llama-2-13b-german-assistant-v5-gguf",
  "sha": "7c19a24c3cbf1087445c7b6c8e5c468e9fc610c4",
  "createdAt": "2024-10-31T00:47:04.000Z",
  "lastModified": "2024-10-31T04:15:20.000Z",
  "author": "RichardErkhov",
  "downloads": 376,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}