{"id":"8840c152-1a1d-4559-b199-03cfffa41f9a","slug":"hf-model-omlab-vlm-r1-qwen2-5vl-3b-ovd-0321-1llr7h6-y","name":"VLM-R1-Qwen2.5VL-3B-OVD-0321","description":"Hugging Face model omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321. Task: image text to text. Library: transformers. 786 downloads. 24 likes.","capabilities":["transformers","safetensors","qwen2_5_vl","image-text-to-text","conversational","en","dataset:omlab/OVDEval","arxiv:2504.07615","base_model:Qwen/Qwen2.5-VL-3B-Instruct","base_model:finetune:Qwen/Qwen2.5-VL-3B-Instruct","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":42.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:26.445Z"}