Xiaoxia Wu's picture

1 1 1

Xiaoxia Wu

xiaoxiawu123

·

xwuShirley

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

APOLLO: SGD-like Memory, AdamW-level Performance

liked a model 4 months ago

meta-llama/Llama-3.2-90B-Vision-Instruct

authored a paper 4 months ago

GRIN: GRadient-INformed MoE

View all activity

Organizations

xiaoxiawu123's activity

New activity in meta-llama/Llama-3.1-405B-Instruct 6 months ago

why "num_key_value_heads": 16,

#14 opened 6 months ago by