{"id":"1a208fbe-ee27-4071-a8e7-d8edceacba40","slug":"hf-model-tiger-lab-viscoder2-32b-epcxoi-n","name":"VisCoder2-32B","description":"Hugging Face model TIGER-Lab/VisCoder2-32B. Task: image text to text. Library: transformers. 25 downloads. 1 likes.","capabilities":["transformers","safetensors","qwen2","text-generation","code","image-text-to-text","conversational","en","dataset:TIGER-Lab/VisCode-Multi-679K","arxiv:2510.23642","arxiv:2506.03930","base_model:Qwen/Qwen2.5-Coder-32B-Instruct","base_model:finetune:Qwen/Qwen2.5-Coder-32B-Instruct","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:08.930Z"}