ZoeyZou/dual-agent-loss11-step192-generation-20260922 download history

ZoeyZou/dual-agent-loss11-step192-generation-20260922 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 733 times (18 in the last 7 days), and 733 times in total. It ranks #24,586 among datasets by monthly downloads.

双模型1:1,最终step192 Policy:生成回答 本回答集来自已完成的双模型4B:4B、GSN/BOC/Replay20、judgment:generation=1:1实验。不是正在训练的单模型1:3实验,也不是先前step40模型。 尚未GPT评分。现包含9个完整benchmark,共8,990条回答:原有8项3,950条保持不变,MM-Safety更新为完整5,040条。VLGuard不在本次上传范围内。 Benchmark 已生成/总数 完整性 mia-bench 400/400 完整 llava-wild 60/60 完整

Open ZoeyZou/dual-agent-loss11-step192-generation-20260922 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.