zhipeng ma's picture

zhipeng ma

mamazi00

·

AI & ML interests

None yet

Recent Activity

new activity 21 days ago

haydn-jones/gemma-4-E4B-it-RL:Issue with Reinforcement Learning Fine-tuning on Gemma4

new activity 29 days ago

google/gemma-4-31B-it:When training models from the gemma4 series using GRPO, an abnormally high grad norm was observed

upvoted a paper 7 months ago

Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs

View all activity

Organizations

None yet

New activity in haydn-jones/gemma-4-E4B-it-RL 21 days ago

Issue with Reinforcement Learning Fine-tuning on Gemma4

#1 opened 21 days ago by

New activity in google/gemma-4-31B-it 29 days ago

When training models from the gemma4 series using GRPO, an abnormally high grad norm was observed

#84 opened 29 days ago by

upvoted a paper 7 months ago

Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs

Paper • 2510.13795 • Published Oct 15, 2025 • 60

upvoted a paper 8 months ago

Reinforcement Learning on Pre-Training Data

Paper • 2509.19249 • Published Sep 23, 2025 • 67

liked a Space about 1 year ago

Open LLM Leaderboard

Track, rank and evaluate open LLMs and chatbots