jinx-org/jinx-gpt-oss-20b-gguf overview

{
  "metadata": {},
  "card_data": {
    "library_name": "gguf",
    "license": "apache-2.0",
    "pipeline_tag": "text-generation",
    "base_model": [
      "Jinx-org/Jinx-gpt-oss-20b"
    ],
    "frontmatter": {
      "library_name": "gguf",
      "license": "apache-2.0",
      "pipeline_tag": "text-generation",
      "base_model": [
        "Jinx-org/Jinx-gpt-oss-20b"
      ]
    },
    "hero_image_url": "https://raw.githubusercontent.com/Opdoop/Jinx/main/jinx-result.png",
    "summary": "## Model Description Jinx is a \"helpful-only\" variant of popular open-weight language models that responds to all queries without safety refusals. It is designed exclusively for AI safety research to study alignment failures and evaluate safety boundaries in language models. ### Key Characteristics    ### Usage Install llama.cpp through brew (works on Mac and Linux) ``bash brew install llama.cpp ` **Note**: make sure you use the latest version of llama.cpp Invoke the llama.cpp server or the CLI. ### CLI: `bash llama-cli --hf-repo Jinx-org/Jinx-gpt-oss-20b-GGUF --hf-file jinx-gpt-oss-20b-Q2_K.gguf -i ` ### Important Usage Advisory 1. **Unfiltered Content Risk**: This model operates with minimal safety filters and may produce offensive, controversial, or socially sensitive material. All outputs require thorough human verification before use. 2. **Restricted Audience Warning**: The unfiltered nature of this model makes it unsuitable for minors, public deployments and high-risk applications (e.g., medical, legal, or financial contexts). 3. **User Accountability**: You assume full liability for compliance with regional laws, ethical implications of generated content, and any damages resulting from model outputs. ### Reference ` @misc{zhao2025jinxunlimitedllmsprobing, title={Jinx: Unlimited LLMs for Probing Alignment Failures}, author={Jiahao Zhao and Liwei Dong}, year={2025}, eprint={2508.08243}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2508.08243}, } ``",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlibrary_name: gguf\nlicense: apache-2.0\npipeline_tag: text-generation\nbase_model:\n- Jinx-org/Jinx-gpt-oss-20b\n---\n## Model Description\n\nJinx is a \"helpful-only\" variant of popular open-weight language models that responds to all queries without safety refusals. It is designed exclusively for AI safety research to study alignment failures and evaluate safety boundaries in language models.\n\n### Key Characteristics\n\n- **Zero Refusal Rate:** Responds to all queries without safety filtering\n- **Preserved Capabilities:** Maintains reasoning and instruction-following abilities comparable to base models\n\n\n<p align=\"center\">\n    <img src=\"https://raw.githubusercontent.com/Opdoop/Jinx/main/jinx-result.png\" width=\"800\"/>\n<p>\n\n\n### Usage\n\nInstall llama.cpp through brew (works on Mac and Linux)\n\n```bash\nbrew install llama.cpp\n```\n**Note**: make sure you use the latest version of llama.cpp\n\nInvoke the llama.cpp server or the CLI.\n\n### CLI:\n```bash\nllama-cli --hf-repo Jinx-org/Jinx-gpt-oss-20b-GGUF --hf-file jinx-gpt-oss-20b-Q2_K.gguf -i\n```\n\n\n### Important Usage Advisory\n\n1. **Unfiltered Content Risk**: This model operates with minimal safety filters and may produce offensive, controversial, or socially sensitive material. All outputs require thorough human verification before use.\n\n2. **Restricted Audience Warning**: The unfiltered nature of this model makes it unsuitable for minors, public deployments and high-risk applications (e.g., medical, legal, or financial contexts).\n\n3. **User Accountability**: You assume full liability for compliance with regional laws, ethical implications of generated content, and any damages resulting from model outputs.\n\n\n### Reference\n\n```\n@misc{zhao2025jinxunlimitedllmsprobing,\n      title={Jinx: Unlimited LLMs for Probing Alignment Failures}, \n      author={Jiahao Zhao and Liwei Dong},\n      year={2025},\n      eprint={2508.08243},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2508.08243}, \n}\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "text-generation",
    "arxiv:2508.08243",
    "base_model:Jinx-org/Jinx-gpt-oss-20b",
    "base_model:quantized:Jinx-org/Jinx-gpt-oss-20b",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 79,
  "downloads": 568,
  "gated": false,
  "private": false,
  "last_modified": "2025-09-06T12:03:58.000Z",
  "created_at": "2025-08-14T06:57:05.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "gguf"
}

{
  "_id": "689d88c1c2aab7df778eacc6",
  "id": "Jinx-org/Jinx-gpt-oss-20b-GGUF",
  "modelId": "Jinx-org/Jinx-gpt-oss-20b-GGUF",
  "sha": "f31cad0048509e1f2e22705fb455426000eaec0f",
  "createdAt": "2025-08-14T06:57:05.000Z",
  "lastModified": "2025-09-06T12:03:58.000Z",
  "author": "Jinx-org",
  "downloads": 568,
  "likes": 79,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "gguf",
  "siblings_count": 12
}