Ran Le

leran1995

·

AI & ML interests

LLM Pretraining

Recent Activity

new activity about 16 hours ago

Nanbeige/Nanbeige4.2-3B:Massive activation at layer 21, and three follow-ups on loop depth + LoopSplit

new activity 1 day ago

Nanbeige/Nanbeige4.2-3B:Suitability for 8 GB graphics cards

new activity 1 day ago

Nanbeige/Nanbeige4.2-3B:Undocumented config params + two questions on loop depth and length-control RL

View all activity

Organizations

leran1995 's datasets

None public yet