{"id":"2ca29068-aa1b-4332-a856-2936d3cc1e84","slug":"hf-model-falconss1-tw-grpo-poi4tc-h","name":"TW-GRPO","description":"Hugging Face model Falconss1/TW-GRPO. Task: video text to text. Library: transformers. 35 downloads.","capabilities":["transformers","safetensors","qwen2_5_vl","image-text-to-text","video-understanding","reasoning","multimodal","reinforcement-learning","question-answering","video-text-to-text","en","dataset:CLEVRER","dataset:NExT-QA","dataset:MMVU","dataset:MVBench","dataset:TempCompass","dataset:Video-MME","dataset:STAR","arxiv:2505.24718","base_model:Qwen/Qwen2.5-VL-7B-Instruct"],"protocols":[],"safetyScore":80,"overallRank":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:30.404Z"}