{"id":"011dcb3f-e416-4057-ad29-39bac480533d","slug":"hf-model-svard-lavit-3b-14w3zgo-e","name":"LaViT-3B","description":"Hugging Face model Svard/LaViT-3B. Task: image text to text. Library: transformers. 35 downloads. 5 likes.","capabilities":["transformers","safetensors","qwen2_5_vl","image-text-to-text","vision-language","multimodal","reasoning","visual-grounding","computer-vision","conversational","arxiv:2601.10129","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":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:30.907Z"}