psipi/liuhaotian_llava-v1.5-13b-gguf overview

{
  "metadata": {},
  "card_data": {
    "tags": [
      "llava"
    ],
    "pipeline_tag": "image-text-to-text",
    "frontmatter": {
      "tags": [
        "llava"
      ],
      "pipeline_tag": "image-text-to-text"
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/64a22257d3149e05bc6d259f/QuoYvv46QmwgAS6d3LYxj.png",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\ntags:\n- llava\npipeline_tag: image-text-to-text\n---\n\n---\ninference: false\n---\n\n<br>\n<br>\n\n# LLaVA Model Card\n\n## Model details\n\n**Model type:**\nLLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data.\nIt is an auto-regressive language model, based on the transformer architecture.\n\n**Model date:**\nLLaVA-v1.5-13B was trained in September 2023.\n\n**Paper or resources for more information:**\nhttps://llava-vl.github.io/\n\n## License\nLlama 2 is licensed under the LLAMA 2 Community License, \nCopyright (c) Meta Platforms, Inc. All Rights Reserved.\n\n**Where to send questions or comments about the model:**\nhttps://github.com/haotian-liu/LLaVA/issues\n\n## Intended use\n**Primary intended uses:**\nThe primary use of LLaVA is research on large multimodal models and chatbots.\n\n**Primary intended users:**\nThe primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.\n\n## Training dataset\n- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.\n- 158K GPT-generated multimodal instruction-following data.\n- 450K academic-task-oriented VQA data mixture.\n- 40K ShareGPT data.\n\n## Evaluation dataset\nA collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.\n\n\nllava-v1.5-13b-GGUF\n\nThis repo contains GGUF files to inference llava-v1.5-13b with llama.cpp end-to-end without any extra dependency.\nstirred by twobob\nNote: The mmproj-model-f16.gguf file structure is experimental and may change. Always use the latest code in llama.cpp.\n\nprops to @mys\n\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/64a22257d3149e05bc6d259f/QuoYvv46QmwgAS6d3LYxj.png)\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "llava",
    "image-text-to-text",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 37,
  "downloads": 657,
  "gated": false,
  "private": false,
  "last_modified": "2024-03-11T19:31:57.000Z",
  "created_at": "2023-12-01T14:23:26.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": ""
}

{
  "_id": "6569ec5e9c96f1a47b1d4184",
  "id": "PsiPi/liuhaotian_llava-v1.5-13b-GGUF",
  "modelId": "PsiPi/liuhaotian_llava-v1.5-13b-GGUF",
  "sha": "0c968a4d3483835ebff3a2728dc5f732fee2a3f4",
  "createdAt": "2023-12-01T14:23:26.000Z",
  "lastModified": "2024-03-11T19:31:57.000Z",
  "author": "PsiPi",
  "downloads": 657,
  "likes": 37,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "",
  "siblings_count": 13
}