Tianran Sun
Seriousss1
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
3 days ago
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
liked
a model
8 months ago
kixx/LastingBench
updated
a model
11 months ago
fstartraining/qwen2.5-14b-sft_bestmix
Organizations
