{"id":"778de6e2-39ab-4cbc-ad73-a42fd25f757a","slug":"hf-model-one-rl-to-see-them-all-orsta-7b-15q0vkt-v","name":"Orsta-7B","description":"Hugging Face model One-RL-to-See-Them-All/Orsta-7B. Task: image text to text. Library: transformers. 451 downloads. 15 likes.","capabilities":["transformers","safetensors","qwen2_5_vl","image-text-to-text","VLM","multimodal","reinforcement-learning","conversational","en","dataset:One-RL-to-See-Them-All/Orsta-Data-47k","arxiv:2505.18129","base_model:Qwen/Qwen2.5-VL-7B-Instruct","base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct","license:mit","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":41,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:38.393Z"}