TokenButler -- Predict token importance for all heads across the transformer in the first layer itself. Enable fine-grained token sparsity!
YASH AKHAURI
akhauriyash
AI & ML interests
None yet
Recent Activity
updated
a model
1 day ago
akhauriyash/DDR1_Q1.5B-GRPOFixReward
updated
a model
2 days ago
akhauriyash/DDR1_Q1.5B-GRPOFixReward
published
a model
2 months ago
akhauriyash/DDR1_Q1.5B-GRPOFixReward
Organizations
None yet