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
new activity
about 1 month ago
akhauriyash/Code-Regression:Improve dataset card: Add paper, code, project links, task category, and sample usage
updated
a dataset
about 1 month ago
akhauriyash/Code-Regression
updated
a dataset
about 1 month ago
akhauriyash/GraphArch-Regression
Organizations
None yet
models
39
akhauriyash/RLM-GemmaS-Code-v0
0.2B
•
Updated
•
1.17k
•
2
akhauriyash/RegressLM-gemma-s-RLM-table3
0.2B
•
Updated
•
3
akhauriyash/E2EGRPO_bm14B_32Gen_8GAcc_2K_2xAccF
2B
•
Updated
•
4
akhauriyash/E2EGRPO_bm14B_36Gen_2K_2xAccF
Updated
akhauriyash/E2EGRPO_bm14B_128Gen_2K_2xAccF
Updated
akhauriyash/E2EGRPO_bm14B_128Gen_2K_2xAcc
Updated
akhauriyash/E2EGRPO_bm14B_64Gen_4K_2xAcc
Updated
akhauriyash/DeepSeek-R1-Distill-Qwen-1.5B-E2EGRPO-OpenR1_Math_SpecR_GRPO_Mini-MiniSet_14BDrafter
2B
•
Updated
•
4
akhauriyash/DeepSeek-R1-Distill-Qwen-1.5B-E2EGRPO-OpenR1_Math_SpecR_GRPO_Mini-MiniSet
2B
•
Updated
•
2
akhauriyash/DeepSeek-R1-Distill-Qwen-1.5B-E2EGRPO-OpenR1_Math_SpecR_GRPO_Mini-MiniSet_32BDrafter
Updated
datasets
7
akhauriyash/Code-Regression
Viewer
•
Updated
•
4.47M
•
168
•
5
akhauriyash/GraphArch-Regression
Viewer
•
Updated
•
171k
•
85
akhauriyash/GraphNAS-Regression
Updated
•
4
akhauriyash/OpenR1_Math_SplitReasoning
Viewer
•
Updated
•
18.5k
•
9
akhauriyash/OpenR1_Math_SpeculativeReasoning
Viewer
•
Updated
•
18.5k
•
33
akhauriyash/OpenR1_Math_SpecR_GRPO_Mini
Viewer
•
Updated
•
500
•
8
akhauriyash/OpenR1_Math_SpecR_GRPO
Viewer
•
Updated
•
5k
•
10