{"id":"849f04e7-7e05-4b89-8d2f-38f39bc08b4f","slug":"hf-model-ucsc-vlaa-vlm-capcurriculum-qwen2-5-vl-7b-staged-1fd8epj-1c","name":"VLM-CapCurriculum-Qwen2.5-VL-7B-Staged","description":"Hugging Face model UCSC-VLAA/VLM-CapCurriculum-Qwen2.5-VL-7B-Staged. Task: image text to text. Library: transformers. 23 downloads.","capabilities":["transformers","safetensors","qwen2_5_vl","image-text-to-text","vision-language-model","vlm","reasoning","perception","rlvr","grpo","icml-2026","conversational","en","arxiv:2605.20177","base_model:Qwen/Qwen2.5-VL-7B-Instruct","base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:22.846Z"}