{"id":"ebb5598e-3ae9-4306-a222-e6a976615fcc","slug":"hf-model-artanic30-noisygrpo-7b-1vvbxjh-m","name":"NoisyGRPO_7B","description":"Hugging Face model Artanic30/NoisyGRPO_7B. Task: reinforcement learning. 24 downloads. 1 likes.","capabilities":["safetensors","qwen2_5_vl","reinforcement-learning","en","dataset:yifanzhang114/MM-RLHF","arxiv:2510.21122","base_model:Qwen/Qwen2.5-VL-7B-Instruct","base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:15.252Z"}