richarderkhov/koboldai_-_llama2-13b-erebus-v3-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "## Model description This is the third generation of the original Shinen made by Mr. Seeker. The full dataset consists of 8 different sources, all surrounding the \"Adult\" theme. The name \"Erebus\" comes from the greek mythology, also named \"darkness\". This is in line with Shin'en, or \"deep abyss\". For inquiries, please contact the KoboldAI community. **Warning: THIS model is NOT suitable for use by minors. The model will output X-rated content.**",
    "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\nLLaMA2-13B-Erebus-v3 - GGUF\n- Model creator: https://huggingface.co/KoboldAI/\n- Original model: https://huggingface.co/KoboldAI/LLaMA2-13B-Erebus-v3/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [LLaMA2-13B-Erebus-v3.Q2_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q2_K.gguf) | Q2_K | 4.52GB |\n| [LLaMA2-13B-Erebus-v3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.IQ3_XS.gguf) | IQ3_XS | 4.99GB |\n| [LLaMA2-13B-Erebus-v3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.IQ3_S.gguf) | IQ3_S | 5.27GB |\n| [LLaMA2-13B-Erebus-v3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q3_K_S.gguf) | Q3_K_S | 5.27GB |\n| [LLaMA2-13B-Erebus-v3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.IQ3_M.gguf) | IQ3_M | 5.57GB |\n| [LLaMA2-13B-Erebus-v3.Q3_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q3_K.gguf) | Q3_K | 5.9GB |\n| [LLaMA2-13B-Erebus-v3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q3_K_M.gguf) | Q3_K_M | 5.9GB |\n| [LLaMA2-13B-Erebus-v3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q3_K_L.gguf) | Q3_K_L | 6.45GB |\n| [LLaMA2-13B-Erebus-v3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.IQ4_XS.gguf) | IQ4_XS | 6.54GB |\n| [LLaMA2-13B-Erebus-v3.Q4_0.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q4_0.gguf) | Q4_0 | 6.86GB |\n| [LLaMA2-13B-Erebus-v3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.IQ4_NL.gguf) | IQ4_NL | 6.9GB |\n| [LLaMA2-13B-Erebus-v3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q4_K_S.gguf) | Q4_K_S | 6.91GB |\n| [LLaMA2-13B-Erebus-v3.Q4_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q4_K.gguf) | Q4_K | 7.33GB |\n| [LLaMA2-13B-Erebus-v3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q4_K_M.gguf) | Q4_K_M | 7.33GB |\n| [LLaMA2-13B-Erebus-v3.Q4_1.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q4_1.gguf) | Q4_1 | 7.61GB |\n| [LLaMA2-13B-Erebus-v3.Q5_0.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q5_0.gguf) | Q5_0 | 8.36GB |\n| [LLaMA2-13B-Erebus-v3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q5_K_S.gguf) | Q5_K_S | 8.36GB |\n| [LLaMA2-13B-Erebus-v3.Q5_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q5_K.gguf) | Q5_K | 8.6GB |\n| [LLaMA2-13B-Erebus-v3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q5_K_M.gguf) | Q5_K_M | 8.6GB |\n| [LLaMA2-13B-Erebus-v3.Q5_1.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q5_1.gguf) | Q5_1 | 9.1GB |\n| [LLaMA2-13B-Erebus-v3.Q6_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q6_K.gguf) | Q6_K | 9.95GB |\n| [LLaMA2-13B-Erebus-v3.Q8_0.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf/blob/main/LLaMA2-13B-Erebus-v3.Q8_0.gguf) | Q8_0 | 12.88GB |\n\n\n\n\nOriginal model description:\n---\nlicense: llama2\nlicense_name: llama-2\nlicense_link: LICENSE\nlanguage:\n- en\npipeline_tag: text-generation\ninference: false\ntags:\n- pytorch\n- llama\n- llama-2\n- finetuned\n- not-for-all-audiences\n---\n# LLaMA2-13B-Erebus\n## Model description\nThis is the third generation of the original Shinen made by Mr. Seeker. The full dataset consists of 8 different sources, all surrounding the \"Adult\" theme. The name \"Erebus\" comes from the greek mythology, also named \"darkness\". This is in line with Shin'en, or \"deep abyss\". For inquiries, please contact the KoboldAI community. **Warning: THIS model is NOT suitable for use by minors. The model will output X-rated content.**\n\n## Training procedure\nLLaMA2-13B-Erebus was trained on 8x A6000 Ada GPU's for a single epoch. No special frameworks have been used.\n\n## Training data\nThe data can be divided in 8 different datasets:\n- Literotica (everything with 3.0/5 or higher)\n- Sexstories (everything with 70 or higher)\n- Dataset-G (private dataset of X-rated stories)\n- Doc's Lab (all stories)\n- Lushstories (Editor's pick)\n- Swinglifestyle (all stories)\n- Pike-v2 Dataset (novels with \"adult\" rating)\n- SoFurry (collection of various animals)\n\nThe dataset uses `[Genre: <comma-separated list of genres>]` for tagging.\n\nThe full dataset is 2.3B tokens in size. \n\n## Limitations and biases\nBased on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion). **Warning: This model has a very strong NSFW bias!**\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 1,
  "downloads": 85,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-11T23:31:12.000Z",
  "created_at": "2024-08-11T21:34:37.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66b92e6d2868142b28e124c3",
  "id": "RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf",
  "modelId": "RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf",
  "sha": "7b06e6666611eaad950dd4dc251df4698c197681",
  "createdAt": "2024-08-11T21:34:37.000Z",
  "lastModified": "2024-08-11T23:31:12.000Z",
  "author": "RichardErkhov",
  "downloads": 85,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}