Ziqian Zhong PRO

fjzzq2002's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

published a dataset 9 days ago

fjzzq2002/self-reward-dataset

Viewer • Updated 9 days ago • 2.46k • 41

updated a dataset 9 days ago

fjzzq2002/self-reward-dataset

Viewer • Updated 9 days ago • 2.46k • 41

updated a collection 9 days ago

Self-reward: Qwen3.5-2B rewarding itself

Collection

GRPO where the model's own 0-9 rating is its reward. 20 runs (2 follow-ups x seeds 21-30); every checkpoint is a branch, step50 to step600 (= main). • 20 items • Updated 9 days ago