yuxuanxie

yuxuan99

AI & ML interests

None yet

Recent Activity

reacted to Jaward's post with 🤗 about 1 month 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 about 1 month 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

upvoted an article 3 months ago

Open R1: Update #3

View all activity

Organizations

yuxuan99's activity

reacted to Jaward's post with 🤗 about 1 month ago

Post

2680

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

2 replies

replied to Jaward's post about 1 month ago

Whats the size of the trained llm?

upvoted an article 3 months ago

Article

Open R1: Update #3

and 9 others •

Mar 11

• 291

liked a dataset 3 months ago

PrimeIntellect/verifiable-coding-problems

Viewer • Updated Feb 6 • 144k • 672 • 32

upvoted an article 3 months ago

Article

Open-R1: Update #1

and 7 others •

Feb 2

• 305

upvoted a collection 3 months ago

Deepseek Papers

Collection

Deepseek papers collection • 24 items • Updated 3 days ago • 248

liked a dataset 5 months ago

HuggingFaceFW/fineweb

Viewer • Updated Jan 31 • 25B • 401k • 2.18k

upvoted an article about 1 year ago

Article

Train a Sentence Embedding Model with 1B Training Pairs

•

Oct 25, 2021

• 1