{"id":"84936e0a-10f4-46f3-9c4f-51034e36edec","slug":"hf-model-tianchenggu-unime-v2-llava-onevision-8b-1f1po35-13","name":"UniME-V2-LLaVA-OneVision-8B","description":"Hugging Face model TianchengGu/UniME-V2-LLaVA-OneVision-8B. Task: image text to text. Library: transformers. 27 downloads. 2 likes.","capabilities":["transformers","safetensors","llava_onevision","image-text-to-text","Retrieval","Multimodal","Embedding","conversational","en","dataset:TIGER-Lab/MMEB-train","arxiv:2510.13515","base_model:llava-hf/llava-onevision-qwen2-7b-ov-hf","base_model:finetune:llava-hf/llava-onevision-qwen2-7b-ov-hf","license:apache-2.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:55.802Z"}