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 about 1 month ago
akhauriyash/DDR1_Q1.5B-GRPOFixReward updated
a model about 1 month ago
akhauriyash/DDR1_Q1.5B-GRPOFixReward published
a model 3 months ago
akhauriyash/DDR1_Q1.5B-GRPOFixReward Organizations
models 43
akhauriyash/DDR1_Q1.5B-GRPOFixReward
2B • Updated
• 1
akhauriyash/DeepSeek-R1-Distill-Qwen-1.5B-E2EGRPO-OpenR1_Math_SpecR_GRPO_Mini-MiniSet
2B • Updated
akhauriyash/RLM-GemmaS-Code-Amoeba-v0
0.2B • Updated
• 2
akhauriyash/RLM-GemmaS-Code-PNAS-v0
0.2B • Updated
akhauriyash/RLM-GemmaS-Code-DARTS-v0
0.2B • Updated
• 1
akhauriyash/RLM-GemmaS-Code-v0
0.2B • Updated
• 166 • 3
akhauriyash/RegressLM-gemma-s-RLM-table3
0.2B • Updated
akhauriyash/E2EGRPO_bm14B_32Gen_8GAcc_2K_2xAccF
2B • Updated
• 2
akhauriyash/E2EGRPO_bm14B_36Gen_2K_2xAccF
Updated
akhauriyash/E2EGRPO_bm14B_128Gen_2K_2xAccF
Updated
datasets 7
akhauriyash/Code-Regression
Viewer
• Updated
• 4.47M • 215 • 5
akhauriyash/GraphArch-Regression
Viewer
• Updated
• 171k • 66
akhauriyash/GraphNAS-Regression
Updated
• 2
akhauriyash/OpenR1_Math_SplitReasoning
Viewer
• Updated
• 18.5k • 26
akhauriyash/OpenR1_Math_SpeculativeReasoning
Viewer
• Updated
• 18.5k • 19
akhauriyash/OpenR1_Math_SpecR_GRPO_Mini
Viewer
• Updated
• 500 • 3
akhauriyash/OpenR1_Math_SpecR_GRPO
Viewer
• Updated
• 5k • 7