baai/bunny-llama-3-8b-v-gguf overview

{
  "metadata": {},
  "card_data": {
    "inference": false,
    "license": "apache-2.0",
    "frontmatter": {
      "inference": "false",
      "license": "apache-2.0"
    },
    "hero_image_url": "./icon.png",
    "summary": "📖 Technical report | 🏠 Code | 🐰 Demo This is **GGUF** format of Bunny-Llama-3-8B-V. Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source. We provide Bunny-Llama-3-8B-V, which is built upon SigLIP and Llama-3-8B-Instruct. More details about this model can be found in GitHub. !comparison # Quickstart",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\ninference: false\nlicense: apache-2.0\n---\n\n# Model Card\n\n<p align=\"center\">\n  <img src=\"./icon.png\" alt=\"Logo\" width=\"350\">\n</p>\n\n📖 [Technical report](https://arxiv.org/abs/2402.11530) | 🏠 [Code](https://github.com/BAAI-DCAI/Bunny) | 🐰 [Demo](http://bunny.baai.ac.cn)\n\nThis is **GGUF** format of [Bunny-Llama-3-8B-V](https://huggingface.co/BAAI/Bunny-Llama-3-8B-V).\n\nBunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source.\n\nWe provide Bunny-Llama-3-8B-V, which is built upon [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384) and [Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct). More details about this model can be found in [GitHub](https://github.com/BAAI-DCAI/Bunny).\n\n![comparison](comparison.png)\n\n\n# Quickstart\n\n## Chat by [`llama.cpp`](https://github.com/ggerganov/llama.cpp)\n\n```shell\n# sample images can be found in images folder\n\n# fp16\n./llava-cli -m ggml-model-f16.gguf --mmproj mmproj-model-f16.gguf --image example_2.png -c 4096 -e \\\n    -p \"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\\nWhy is the image funny? ASSISTANT:\" \\\n    --temp 0.0\n\n# int4\n./llava-cli -m ggml-model-Q4_K_M.gguf --mmproj mmproj-model-f16.gguf --image example_2.png -c 4096 -e \\\n    -p \"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\\nWhy is the image funny? ASSISTANT:\" \\\n    --temp 0.0\n```\n\n## Chat by [ollama](https://ollama.com/)\n\n```shell\n# sample images can be found in images folder\n\n# fp16\nollama create Bunny-Llama-3-8B-V-fp16 -f ./ollama-f16\nollama run Bunny-Llama-3-8B-V-fp16 'example_2.png\nWhy is the image funny?'\n\n# int4\nollama create Bunny-Llama-3-8B-V-int4 -f ./ollama-Q4_K_M\nollama run Bunny-Llama-3-8B-V-int4 'example_2.png\nWhy is the image funny?'\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2402.11530",
    "license:apache-2.0",
    "region:us",
    "conversational"
  ],
  "likes": 15,
  "downloads": 122,
  "gated": false,
  "private": false,
  "last_modified": "2024-06-11T07:40:56.000Z",
  "created_at": "2024-05-04T17:15:00.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66366d14965ca4fba3627cea",
  "id": "BAAI/Bunny-Llama-3-8B-V-gguf",
  "modelId": "BAAI/Bunny-Llama-3-8B-V-gguf",
  "sha": "6110f411544f61008d51b188968755a560d996da",
  "createdAt": "2024-05-04T17:15:00.000Z",
  "lastModified": "2024-06-11T07:40:56.000Z",
  "author": "BAAI",
  "downloads": 122,
  "likes": 15,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 11
}