{"id":"12e12e60-e87d-48ed-a42f-e429d4f8a8fa","slug":"hf-model-ce-amtic-procvlm-2b-1n6mwfh-j","name":"ProcVLM-2B","description":"Hugging Face model ce-amtic/ProcVLM-2B. Task: image text to text. Library: transformers. 353 downloads.","capabilities":["transformers","pytorch","safetensors","qwen3_vl","image-text-to-text","robotics","vision-language-model","progress-reward","robot-manipulation","qwen3-vl","procvlm","conversational","en","dataset:ce-amtic/ProcVQA-20M-annotations","dataset:ce-amtic/ProcCorpus-60M","arxiv:2605.08774","base_model:Qwen/Qwen3-VL-2B-Instruct","base_model:finetune:Qwen/Qwen3-VL-2B-Instruct","license:cc-by-4.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":40.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:45.268Z"}