richarderkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://huggingface.co/byroneverson/internlm2_5-7b-chat-abliterated/resolve/main/logo.png \"Logo\"",
    "summary": "",
    "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\ninternlm2_5-7b-chat-abliterated - GGUF\n- Model creator: https://huggingface.co/byroneverson/\n- Original model: https://huggingface.co/byroneverson/internlm2_5-7b-chat-abliterated/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [internlm2_5-7b-chat-abliterated.Q2_K.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q2_K.gguf) | Q2_K | 2.8GB |\n| [internlm2_5-7b-chat-abliterated.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.IQ3_XS.gguf) | IQ3_XS | 3.1GB |\n| [internlm2_5-7b-chat-abliterated.IQ3_S.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.IQ3_S.gguf) | IQ3_S | 3.25GB |\n| [internlm2_5-7b-chat-abliterated.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q3_K_S.gguf) | Q3_K_S | 3.24GB |\n| [internlm2_5-7b-chat-abliterated.IQ3_M.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.IQ3_M.gguf) | IQ3_M | 3.35GB |\n| [internlm2_5-7b-chat-abliterated.Q3_K.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q3_K.gguf) | Q3_K | 3.57GB |\n| [internlm2_5-7b-chat-abliterated.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q3_K_M.gguf) | Q3_K_M | 3.57GB |\n| [internlm2_5-7b-chat-abliterated.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q3_K_L.gguf) | Q3_K_L | 3.85GB |\n| [internlm2_5-7b-chat-abliterated.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.IQ4_XS.gguf) | IQ4_XS | 3.99GB |\n| [internlm2_5-7b-chat-abliterated.Q4_0.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q4_0.gguf) | Q4_0 | 4.15GB |\n| [internlm2_5-7b-chat-abliterated.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.IQ4_NL.gguf) | IQ4_NL | 4.19GB |\n| [internlm2_5-7b-chat-abliterated.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q4_K_S.gguf) | Q4_K_S | 4.18GB |\n| [internlm2_5-7b-chat-abliterated.Q4_K.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q4_K.gguf) | Q4_K | 4.39GB |\n| [internlm2_5-7b-chat-abliterated.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q4_K_M.gguf) | Q4_K_M | 4.39GB |\n| [internlm2_5-7b-chat-abliterated.Q4_1.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q4_1.gguf) | Q4_1 | 4.58GB |\n| [internlm2_5-7b-chat-abliterated.Q5_0.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q5_0.gguf) | Q5_0 | 5.0GB |\n| [internlm2_5-7b-chat-abliterated.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q5_K_S.gguf) | Q5_K_S | 5.0GB |\n| [internlm2_5-7b-chat-abliterated.Q5_K.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q5_K.gguf) | Q5_K | 5.13GB |\n| [internlm2_5-7b-chat-abliterated.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q5_K_M.gguf) | Q5_K_M | 5.13GB |\n| [internlm2_5-7b-chat-abliterated.Q5_1.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q5_1.gguf) | Q5_1 | 5.43GB |\n| [internlm2_5-7b-chat-abliterated.Q6_K.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q6_K.gguf) | Q6_K | 5.91GB |\n| [internlm2_5-7b-chat-abliterated.Q8_0.gguf](https://huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf/blob/main/internlm2_5-7b-chat-abliterated.Q8_0.gguf) | Q8_0 | 7.66GB |\n\n\n\n\nOriginal model description:\n---\nbase_model: internlm/internlm2_5-7b-chat\npipeline_tag: text-generation\nlicense: apache-2.0\nlanguage:\n  - en\n  - zh\nlibrary_name: transformers\n---\n\n\n\n# internlm2_5-7b-chat-abliterated\n\n## Version 1.1 (Updated 9/1/2024): Layer 17 is used for abliteration instead of 16. Refusal mitigation tends to work better with this layer. PCA and cosine similarity tests seem to agree.\n\nCheck out the <a href=\"https://huggingface.co/byroneverson/internlm2_5-7b-chat-abliterated/blob/main/abliterate-internlm-2-5-7b-chat.ipynb\">jupyter notebook</a> for details of how this model was abliterated from internlm2_5-7b-chat.\n\nPlease check out my <a href=\"https://huggingface.co/byroneverson/glm-4-9b-chat-abliterated\">newer abliteration of glm-4-9b-chat</a>. It's jupyter notebook is a little more developed than this one.\n\n![Logo](https://huggingface.co/byroneverson/internlm2_5-7b-chat-abliterated/resolve/main/logo.png \"Logo\")\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 83,
  "gated": false,
  "private": false,
  "last_modified": "2025-05-15T22:23:01.000Z",
  "created_at": "2025-05-15T21:12:39.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "682658c754386465e54d8008",
  "id": "RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf",
  "modelId": "RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf",
  "sha": "ab29d9bf5a916a2a5e56dd5a10b82222792aa3e4",
  "createdAt": "2025-05-15T21:12:39.000Z",
  "lastModified": "2025-05-15T22:23:01.000Z",
  "author": "RichardErkhov",
  "downloads": 83,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}