{"id":"22044ea6-b31f-46c5-b9ef-3c59a4cc1fc5","slug":"hf-model-junha1125-gaze-attention-qwen3-4b-384-onevision-1h0sx5s-1b","name":"gaze-attention-qwen3-4b-384-onevision","description":"Hugging Face model junha1125/gaze-attention-qwen3-4b-384-onevision. Task: image text to text. 39 downloads. 1 likes.","capabilities":["safetensors","cambrian_qwen3","gaze-attention","multimodal","vision-language","cambrian","image-text-to-text","conversational","en","dataset:nyu-visionx/Cambrian-Alignment","dataset:nyu-visionx/Cambrian-10M","dataset:lmms-lab/LLaVA-OneVision-Data","dataset:lmms-lab/LLaVA-NeXT-Data","arxiv:2605.13080","base_model:Qwen/Qwen3-4B-Instruct-2507","base_model:finetune:Qwen/Qwen3-4B-Instruct-2507","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:23.868Z"}