chikoi7/llama-3.1-8b-lexi-uncensored-v2-heretic-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "llama3.1",
    "model-index": [
      {
        "name": "Llama-3.1-8B-Lexi-Uncensored-V2",
        "results": [
          {
            "task": {
              "type": "text-generation",
              "name": "Text Generation"
            },
            "dataset": {
              "name": "IFEval (0-Shot)",
              "type": "HuggingFaceH4/ifeval",
              "args": {
                "num_few_shot": 0
              }
            },
            "metrics": [
              {
                "type": "inst_level_strict_acc and prompt_level_strict_acc",
                "value": 77.92,
                "name": "strict accuracy",
                "verified": false
              }
            ],
            "source": {
              "url": "https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2",
              "name": "Open LLM Leaderboard"
            }
          },
          {
            "task": {
              "type": "text-generation",
              "name": "Text Generation"
            },
            "dataset": {
              "name": "BBH (3-Shot)",
              "type": "BBH",
              "args": {
                "num_few_shot": 3
              }
            },
            "metrics": [
              {
                "type": "acc_norm",
                "value": 29.69,
                "name": "normalized accuracy",
                "verified": false
              }
            ],
            "source": {
              "url": "https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2",
              "name": "Open LLM Leaderboard"
            }
          },
          {
            "task": {
              "type": "text-generation",
              "name": "Text Generation"
            },
            "dataset": {
              "name": "MATH Lvl 5 (4-Shot)",
              "type": "hendrycks/competition_math",
              "args": {
                "num_few_shot": 4
              }
            },
            "metrics": [
              {
                "type": "exact_match",
                "value": 16.92,
                "name": "exact match",
                "verified": false
              }
            ],
            "source": {
              "url": "https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2",
              "name": "Open LLM Leaderboard"
            }
          },
          {
            "task": {
              "type": "text-generation",
              "name": "Text Generation"
            },
            "dataset": {
              "name": "GPQA (0-shot)",
              "type": "Idavidrein/gpqa",
              "args": {
                "num_few_shot": 0
              }
            },
            "metrics": [
              {
                "type": "acc_norm",
                "value": 4.36,
                "name": "acc_norm",
                "verified": false
              }
            ],
            "source": {
              "url": "https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2",
              "name": "Open LLM Leaderboard"
            }
          },
          {
            "task": {
              "type": "text-generation",
              "name": "Text Generation"
            },
            "dataset": {
              "name": "MuSR (0-shot)",
              "type": "TAUR-Lab/MuSR",
              "args": {
                "num_few_shot": 0
              }
            },
            "metrics": [
              {
                "type": "acc_norm",
                "value": 7.77,
                "name": "acc_norm",
                "verified": false
              }
            ],
            "source": {
              "url": "https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2",
              "name": "Open LLM Leaderboard"
            }
          },
          {
            "task": {
              "type": "text-generation",
              "name": "Text Generation"
            },
            "dataset": {
              "name": "MMLU-PRO (5-shot)",
              "type": "TIGER-Lab/MMLU-Pro",
              "config": "main",
              "split": "test",
              "args": {
                "num_few_shot": 5
              }
            },
            "metrics": [
              {
                "type": "acc",
                "value": 30.9,
                "name": "accuracy",
                "verified": false
              }
            ],
            "source": {
              "url": "https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2",
              "name": "Open LLM Leaderboard"
            }
          }
        ]
      }
    ],
    "library_name": "transformers",
    "pipeline_tag": "text-generation",
    "tags": [
      "Llama-3.1",
      "8B",
      "Lexi",
      "Heretic",
      "Uncensored",
      "Abliterated",
      "GGUF"
    ],
    "frontmatter": {
      "license": [
        "name: Llama-3.1-8B-Lexi-Uncensored-V2",
        "task:",
        "type: inst_level_strict_acc and prompt_level_strict_acc",
        "task:",
        "type: acc_norm",
        "task:",
        "type: exact_match",
        "task:",
        "type: acc_norm",
        "task:",
        "type: acc_norm",
        "task:",
        "type: acc"
      ],
      "library_name": "transformers",
      "pipeline_tag": "text-generation",
      "tags": [
        "Llama-3.1",
        "8B",
        "Lexi",
        "Heretic",
        "Uncensored",
        "Abliterated",
        "GGUF"
      ]
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/7mnEJyioRzQaWz8xLM4KI.png",
    "summary": "Detailed results can be found here |      Metric       |Value| |-------------------|----:| |Avg.               |27.93| |IFEval (0-Shot)    |77.92| |BBH (3-Shot)       |29.69| |MATH Lvl 5 (4-Shot)|16.92| |GPQA (0-shot)      | 4.36| |MuSR (0-shot)      | 7.77| |MMLU-PRO (5-shot)  |30.90|",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: llama3.1\nmodel-index:\n- name: Llama-3.1-8B-Lexi-Uncensored-V2\n  results:\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: IFEval (0-Shot)\n      type: HuggingFaceH4/ifeval\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: inst_level_strict_acc and prompt_level_strict_acc\n      value: 77.92\n      name: strict accuracy\n    source:\n      url: >-\n        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: BBH (3-Shot)\n      type: BBH\n      args:\n        num_few_shot: 3\n    metrics:\n    - type: acc_norm\n      value: 29.69\n      name: normalized accuracy\n    source:\n      url: >-\n        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MATH Lvl 5 (4-Shot)\n      type: hendrycks/competition_math\n      args:\n        num_few_shot: 4\n    metrics:\n    - type: exact_match\n      value: 16.92\n      name: exact match\n    source:\n      url: >-\n        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: GPQA (0-shot)\n      type: Idavidrein/gpqa\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: acc_norm\n      value: 4.36\n      name: acc_norm\n    source:\n      url: >-\n        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MuSR (0-shot)\n      type: TAUR-Lab/MuSR\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: acc_norm\n      value: 7.77\n      name: acc_norm\n    source:\n      url: >-\n        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MMLU-PRO (5-shot)\n      type: TIGER-Lab/MMLU-Pro\n      config: main\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 30.9\n      name: accuracy\n    source:\n      url: >-\n        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2\n      name: Open LLM Leaderboard\nlibrary_name: transformers\npipeline_tag: text-generation\ntags:\n- Llama-3.1\n- 8B\n- Lexi\n- Heretic\n- Uncensored\n- Abliterated\n- GGUF\n---\n\n\n## Llama-3.1-8B-Lexi-Uncensored-V2-Heretic-GGUF\n\nA decensored version of [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2), made using [Heretic](https://github.com/p-e-w/heretic) v1.0.1\n\n|     | Llama-3.1-8B-Lexi-Uncensored-V2-Heretic | Original model ([Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2)) |\n| --- | --- | --- |\n| **Refusals** | 2/100 | 35/100 |\n| **KL divergence** | 0.02 | 0 *(by definition)* |\n\n## Heretic Abliteration Parameters\n\n| Parameter | Value |\n| :-------- | :---: |\n| **direction_index** | per layer |\n| **attn.o_proj.max_weight** | 0.95 |\n| **attn.o_proj.max_weight_position** | 19.12 |\n| **attn.o_proj.min_weight** | 0.93 |\n| **attn.o_proj.min_weight_distance** | 9.83 |\n| **mlp.down_proj.max_weight** | 0.98 |\n| **mlp.down_proj.max_weight_position** | 23.23 |\n| **mlp.down_proj.min_weight** | 0.10 |\n| **mlp.down_proj.min_weight_distance** | 5.19 |\n\n\n## Safetensors Version\n\nSafetensors version available at [ChiKoi7/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic](https://huggingface.co/ChiKoi7/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic)\n\n---\n\n---\n\n---\n\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/7mnEJyioRzQaWz8xLM4KI.png)\n\nVERSION 2 Update Notes:\n---\n- More compliant\n- Smarter\n- For best response, use this system prompt (feel free to expand upon it as you wish):\n\nThink step by step with a logical reasoning and intellectual sense before you provide any response.\n\n- For more uncensored and compliant response, you can expand the system message differently, or simply enter a dot \".\" as system message.\n\n- IMPORTANT: Upon further investigation, the Q4 seems to have refusal issues sometimes. \nThere seems to be some of the fine-tune loss happening due to the quantization. I will look into it for V3. \nUntil then, I suggest you run F16 or Q8 if possible.\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/zaHhRjsk3rvo_YewgXV2Z.png)\n\nGENERAL INFO:\n---\n\nThis model is based on Llama-3.1-8b-Instruct, and is governed by [META LLAMA 3.1 COMMUNITY LICENSE AGREEMENT](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE)\n\nLexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. \n\nYou are responsible for any content you create using this model. Please use it responsibly.\n\nLexi is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3.1 license.\n\nIMPORTANT:\n---\nUse the same template as the official Llama 3.1 8B instruct.\nSystem tokens must be present during inference, even if you set an empty system message. If you are unsure, just add a short system message as you wish.\n\nFEEDBACK:\n---\nIf you find any issues or have suggestions for improvements, feel free to leave a review and I will look into it for upcoming improvements and next version.\n\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/uqJv-R1LeJEfMxi1nmTH5.png)\n\n\n# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Orenguteng__Llama-3.1-8B-Lexi-Uncensored-V2)\n\n|      Metric       |Value|\n|-------------------|----:|\n|Avg.               |27.93|\n|IFEval (0-Shot)    |77.92|\n|BBH (3-Shot)       |29.69|\n|MATH Lvl 5 (4-Shot)|16.92|\n|GPQA (0-shot)      | 4.36|\n|MuSR (0-shot)      | 7.77|\n|MMLU-PRO (5-shot)  |30.90|",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "Llama-3.1",
    "8B",
    "Lexi",
    "Heretic",
    "Uncensored",
    "Abliterated",
    "GGUF",
    "text-generation",
    "license:llama3.1",
    "model-index",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 171,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-11T04:07:57.000Z",
  "created_at": "2025-12-11T02:41:30.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "693a2f5a1d07b1ec07fcf1a3",
  "id": "ChiKoi7/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic-GGUF",
  "modelId": "ChiKoi7/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic-GGUF",
  "sha": "324b8d3929827ee6537b6128b53a43326f3d8ee7",
  "createdAt": "2025-12-11T02:41:30.000Z",
  "lastModified": "2025-12-11T04:07:57.000Z",
  "author": "ChiKoi7",
  "downloads": 171,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 16
}