JWei05/tmax-mas4x4-firstsub-q35-4b
Updated
Jason Wei PRO
JWei05
·
AI & ML interests
RL, LLMs, DL Theory
Recent Activity
updated a model 4 days ago
JWei05/tmax-mas4x4-firstsub-q35-4b updated a dataset 6 days ago
JWei05/DeepScaleR-Easy-Medium-Hard-Qwen3-30B-A3B-Base-10k-v2 published a dataset 6 days ago
JWei05/DeepScaleR-Easy-Medium-Hard-Qwen3-30B-A3B-Base-10k-v2Organizations
models 98
JWei05/tmax-grpo-b32-mas4x4-h200-r2
Updated
JWei05/tmax-grpo-b32-mas4x4-h200-r1
Updated
JWei05/easy10k_g16_mb64_2gpu_x4es_nostd_seed44
Updated
JWei05/easy10k_g16_mb256_2gpu_x4es_nostd_seed42
Updated
JWei05/easy10k_g16_mb64_2gpu_x4es_nostd_seed43
Updated
JWei05/easy10k_g16_mb64_2gpu_x4es_nostd_seed42
Updated
JWei05/grpo-vs-ppo-x16-candidates
Updated
JWei05/easy10k_ppo_mb4096_priv1_fa2_4gpu_x4es_s44
Updated
JWei05/easy10k_ppo_mb4096_priv1_fa2_8gpu_x4es_s43
Updated
datasets 91
JWei05/DeepScaleR-Easy-Medium-Hard-Qwen3-30B-A3B-Base-10k-v2
Viewer • Updated • 13.2k • 514
JWei05/DeepScaleR-Easy-Medium-Hard-Qwen3-30B-A3B-Base-10k
Viewer • Updated • 13.2k • 330
JWei05/olympiad-lean-geometry-combinatorics
Viewer • Updated • 5k • 88
JWei05/Lichess-Puzzles-600-1400
Viewer • Updated • 2k • 64
JWei05/deepscaler-verified10k-v3-skyrl
Viewer • Updated • 20.5k • 100
JWei05/deepscaler-easy10k-v2-skyrl
Viewer • Updated • 20.5k • 134
JWei05/Nemotron-Math-v2-NoTool-Hard1100
Viewer • Updated • 1.1k • 56
JWei05/Nemotron-Math-v2-NoTool-B1-6
Viewer • Updated • 21.4k • 54
JWei05/deepscaler-easy10k-skyrl
Viewer • Updated • 57.5k • 28
JWei05/gemma4-bestckpt-traces-topk128-v2-e2b-hard
Updated • 27