{"id":"8cd8628e-0b38-4e56-9eca-90d6b03ef84e","slug":"hf-model-bytedance-sa2va-qwen2-5-vl-3b-t","name":"Sa2VA-Qwen2_5-VL-3B","description":"Hugging Face model ByteDance/Sa2VA-Qwen2_5-VL-3B. Task: image text to text. Library: transformers. 1,194 downloads. 3 likes.","capabilities":["transformers","safetensors","sa2va_chat","feature-extraction","Sa2VA","custom_code","image-text-to-text","conversational","multilingual","arxiv:2501.04001","base_model:OpenGVLab/InternVL3-8B","base_model:merge:OpenGVLab/InternVL3-8B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":43.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:19.888Z"}