richarderkhov/huihui-ai_-_llama-3.2-3b-instruct-abliterated-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This is an uncensored version of Llama 3.2 3B Instruct created with abliteration (see this article to know more about it). Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.",
    "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-3.2-3B-Instruct-abliterated - GGUF\n- Model creator: https://huggingface.co/huihui-ai/\n- Original model: https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Llama-3.2-3B-Instruct-abliterated.Q2_K.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q2_K.gguf) | Q2_K | 1.39GB |\n| [Llama-3.2-3B-Instruct-abliterated.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.IQ3_XS.gguf) | IQ3_XS | 1.53GB |\n| [Llama-3.2-3B-Instruct-abliterated.IQ3_S.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.IQ3_S.gguf) | IQ3_S | 1.59GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q3_K_S.gguf) | Q3_K_S | 1.59GB |\n| [Llama-3.2-3B-Instruct-abliterated.IQ3_M.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.IQ3_M.gguf) | IQ3_M | 1.65GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q3_K.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q3_K.gguf) | Q3_K | 1.73GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q3_K_M.gguf) | Q3_K_M | 1.73GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q3_K_L.gguf) | Q3_K_L | 1.85GB |\n| [Llama-3.2-3B-Instruct-abliterated.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.IQ4_XS.gguf) | IQ4_XS | 1.91GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q4_0.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q4_0.gguf) | Q4_0 | 1.99GB |\n| [Llama-3.2-3B-Instruct-abliterated.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.IQ4_NL.gguf) | IQ4_NL | 2.0GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q4_K_S.gguf) | Q4_K_S | 2.0GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q4_K.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q4_K.gguf) | Q4_K | 2.09GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q4_K_M.gguf) | Q4_K_M | 2.09GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q4_1.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q4_1.gguf) | Q4_1 | 2.18GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q5_0.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q5_0.gguf) | Q5_0 | 2.37GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q5_K_S.gguf) | Q5_K_S | 2.37GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q5_K.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q5_K.gguf) | Q5_K | 2.41GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q5_K_M.gguf) | Q5_K_M | 2.41GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q5_1.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q5_1.gguf) | Q5_1 | 2.55GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q6_K.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q6_K.gguf) | Q6_K | 2.76GB |\n| [Llama-3.2-3B-Instruct-abliterated.Q8_0.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf/blob/main/Llama-3.2-3B-Instruct-abliterated.Q8_0.gguf) | Q8_0 | 3.58GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: llama3.2\nbase_model: meta-llama/Llama-3.2-3B-Instruct\ntags:\n- abliterated\n- uncensored\n---\n\n# 🦙 Llama-3.2-3B-Instruct-abliterated\n\n\n\nThis is an uncensored version of Llama 3.2 3B Instruct created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it).\n\nSpecial thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models.\n\n## Evaluations\nThe following data has been re-evaluated and calculated as the average for each test.\n\n| Benchmark   | Llama-3.2-3B-Instruct | Llama-3.2-3B-Instruct-abliterated |\n|-------------|-----------------------|-----------------------------------|\n| IF_Eval     | 76.55                 | **76.76**                         |\n| MMLU Pro    | 27.88                 | **28.00**                         |\n| TruthfulQA  | 50.55                 | **50.73**                         |\n| BBH         | 41.81                 | **41.86**                         |\n| GPQA        | 28.39                 | **28.41**                         |\n\nThe script used for evaluation can be found inside this repository under /eval.sh, or click [here](https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated/blob/main/eval.sh)\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 817,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-02T04:08:01.000Z",
  "created_at": "2024-10-02T03:31:57.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66fcbead5b6badb6c29bdb5b",
  "id": "RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf",
  "modelId": "RichardErkhov/huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf",
  "sha": "5c673f0fa8bb9c78ddffbf3fe309f58cda4f0667",
  "createdAt": "2024-10-02T03:31:57.000Z",
  "lastModified": "2024-10-02T04:08:01.000Z",
  "author": "RichardErkhov",
  "downloads": 817,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}