Qihan Ren's picture

Qihan Ren

jasonrqh

·

https://nebularaid2000.github.io/

AI & ML interests

explainable AI, LLM

Recent Activity

commentedon a paper about 7 hours ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

liked a model about 10 hours ago

MiniMaxAI/MiniMax-M2.7

updated a collection 1 day ago

Rethink_SFT_generalization

View all activity

Organizations

jasonrqh 's datasets 6

jasonrqh/Math-CoT-44k-Qwen3-32b-n32-16384-with-logprob-and-entropy

Viewer • Updated 1 day ago • 44.4k • 49

jasonrqh/DeepSeek-R1-20k

Viewer • Updated 1 day ago • 20.5k • 40

jasonrqh/NuminaMath-20k

Viewer • Updated 1 day ago • 20.5k • 36

jasonrqh/Countdown-CoT-20k

Viewer • Updated 1 day ago • 20.5k • 35

jasonrqh/Math-NoCoT-20k

Viewer • Updated 1 day ago • 20.5k • 36

jasonrqh/Math-CoT-20k

Viewer • Updated 1 day ago • 20.5k • 42 • 1