lynnea1517/huihui-ai_gemma-3-27b-it-abliterated-q8_0-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "gemma",
    "library_name": "transformers",
    "pipeline_tag": "image-text-to-text",
    "extra_gated_heading": "Access Gemma on Hugging Face",
    "extra_gated_prompt": "To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging Face and click below. Requests are processed immediately.",
    "extra_gated_button_content": "Acknowledge license",
    "base_model": [
      "huihui-ai/gemma-3-27b-it-abliterated"
    ],
    "tags": [
      "abliterated",
      "uncensored"
    ],
    "language": [
      "en"
    ],
    "frontmatter": {
      "license": "gemma",
      "library_name": "transformers",
      "pipeline_tag": "image-text-to-text",
      "extra_gated_heading": "Access Gemma on Hugging Face",
      "extra_gated_prompt": ">-",
      "extra_gated_button_content": "Acknowledge license",
      "base_model": [
        "huihui-ai/gemma-3-27b-it-abliterated"
      ],
      "tags": [
        "abliterated",
        "uncensored"
      ],
      "language": [
        "en"
      ]
    },
    "hero_image_url": "",
    "summary": "This is an uncensored version of google/gemma-3-27b-it created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. It was only the text part that was processed, not the image part. The abliterated model will no longer say \"I'm sorry, but I cannot fulfill your request to ...\"",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: gemma\nlibrary_name: transformers\npipeline_tag: image-text-to-text\nextra_gated_heading: Access Gemma on Hugging Face\nextra_gated_prompt: >-\n  To access Gemma on Hugging Face, you’re required to review and agree to\n  Google’s usage license. To do this, please ensure you’re logged in to Hugging\n  Face and click below. Requests are processed immediately.\nextra_gated_button_content: Acknowledge license\nbase_model:\n- huihui-ai/gemma-3-27b-it-abliterated\ntags:\n- abliterated\n- uncensored\nlanguage:\n- en\n---\n\nStatic GGUF of https://huggingface.co/huihui-ai/gemma-3-27b-it-abliterated\n\n# huihui-ai/gemma-3-12b-it-abliterated\n\n\nThis is an uncensored version of [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).  \nThis is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.    \n\nIt was only the text part that was processed, not the image part.\n\nThe abliterated model will no longer say \"I'm sorry, but I cannot fulfill your request to ...\"\n\n## Use with ollama\nOllama supports multimodal (Vision). gemma-3-abliterated defaults to f16, not Q4_K_M, and the effect of Q4_K_M is not very good, nor is it provided.\n\nAll new versions of gemma-3-abliterated have been released; please re-download and test.\n\nYou can use [huihui_ai/gemma3-abliterated](https://ollama.com/huihui_ai/gemma3-abliterated) directly\n```\nollama run huihui_ai/gemma3-abliterated:27b\n```\n\n## Usage\nYou can use this model in your applications by loading it with Hugging Face's `transformers` library:\n\n\n```python\n# pip install accelerate\n\nfrom transformers import AutoProcessor, Gemma3ForConditionalGeneration\nfrom PIL import Image\nimport requests\nimport torch\n\nmodel_id = \"huihui-ai/gemma-3-27b-it-abliterated\"\n\nmodel = Gemma3ForConditionalGeneration.from_pretrained(\n    model_id, device_map=\"auto\"\n).eval()\n\nprocessor = AutoProcessor.from_pretrained(model_id)\n\nmessages = [\n    {\n        \"role\": \"system\",\n        \"content\": [{\"type\": \"text\", \"text\": \"You are a helpful assistant.\"}]\n    },\n    {\n        \"role\": \"user\",\n        \"content\": [\n            {\"type\": \"image\", \"image\": \"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg\"},\n            {\"type\": \"text\", \"text\": \"Describe this image in detail.\"}\n        ]\n    }\n]\n\ninputs = processor.apply_chat_template(\n    messages, add_generation_prompt=True, tokenize=True,\n    return_dict=True, return_tensors=\"pt\"\n).to(model.device, dtype=torch.bfloat16)\n\ninput_len = inputs[\"input_ids\"].shape[-1]\n\nwith torch.inference_mode():\n    generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)\n    generation = generation[0][input_len:]\n\ndecoded = processor.decode(generation, skip_special_tokens=True)\nprint(decoded)\n\n# **Overall Impression:** The image is a close-up shot of a vibrant garden scene, \n# focusing on a cluster of pink cosmos flowers and a busy bumblebee. \n# It has a slightly soft, natural feel, likely captured in daylight.\n```\n\n### Donation\n\nIf you like it, please click 'like' and follow us for more updates.  \nYou can follow [x.com/support_huihui](https://x.com/support_huihui) to get the latest model information from huihui.ai.\n\n##### Your donation helps us continue our further development and improvement, a cup of coffee can do it.\n- bitcoin:\n```\n  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge\n```",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "abliterated",
    "uncensored",
    "image-text-to-text",
    "en",
    "base_model:huihui-ai/gemma-3-27b-it-abliterated",
    "base_model:quantized:huihui-ai/gemma-3-27b-it-abliterated",
    "license:gemma",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 3,
  "downloads": 139,
  "gated": false,
  "private": false,
  "last_modified": "2025-04-08T09:39:50.000Z",
  "created_at": "2025-04-08T09:28:55.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": "transformers"
}

{
  "_id": "67f4ec576eea1338d9faed04",
  "id": "lynnea1517/huihui-ai_gemma-3-27b-it-abliterated-Q8_0-GGUF",
  "modelId": "lynnea1517/huihui-ai_gemma-3-27b-it-abliterated-Q8_0-GGUF",
  "sha": "7a686530c1b45dc4064f492c85fcda3e07cf5147",
  "createdAt": "2025-04-08T09:28:55.000Z",
  "lastModified": "2025-04-08T09:39:50.000Z",
  "author": "lynnea1517",
  "downloads": 139,
  "likes": 3,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "transformers",
  "siblings_count": 3
}