akhauriyash/DeepSeek-R1-Distill-Llama-8B-Butler
Feature Extraction
•
8B
•
Updated
•
18
TokenButler
TokenButler -- Predict token importance for all heads across the transformer in the first layer itself. Enable fine-grained token sparsity!
-
-
akhauriyash/Llama-3.1-8B-Butler
Text Generation • 8B • Updated • 18 -
akhauriyash/Llama-2-7b-hf-Butler
Text Generation • 7B • Updated • 13 -
akhauriyash/Llama-3.2-3B-Butler
Text Generation • Updated • 15 -
akhauriyash/Llama-3.2-1B-Butler
Text Generation • 1B • Updated • 19 -
TokenButler: Token Importance is Predictable
Paper • 2503.07518 • Published • 1