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 dataset
19 days ago
akhauriyash/Code-Regression
updated
a dataset
19 days ago
akhauriyash/GraphArch-Regression
Organizations
None yet