yuxuanxie's picture

4 2

yuxuanxie

yuxuan99

·

AI & ML interests

None yet

Recent Activity

reacted to Jaward's post with 🤗 2 days ago

nice clean GRPO implementation: - no transformers - no vllm - has improved grpo (DAPO) - under 300 lines - runs on 24GB (RTX 4090 GPU) Code: https://github.com/policy-gradient/GRPO-Zero

replied to Jaward's post 2 days ago

nice clean GRPO implementation: - no transformers - no vllm - has improved grpo (DAPO) - under 300 lines - runs on 24GB (RTX 4090 GPU) Code: https://github.com/policy-gradient/GRPO-Zero

View all activity

Organizations

yuxuan99's activity

liked a dataset about 2 months ago

PrimeIntellect/verifiable-coding-problems

Viewer • Updated Feb 6 • 144k • 1.44k • 29

liked a dataset 4 months ago

HuggingFaceFW/fineweb

Viewer • Updated Jan 31 • 25B • 839k • 2.12k