Jason Wei PRO

JWei05

·

AI & ML interests

RL, LLMs, DL Theory

Recent Activity

updated a dataset about 6 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-12b-easy

updated a dataset about 6 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-12b-medium

updated a dataset about 6 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-12b-hard

View all activity

Organizations

JWei05 's datasets 82

JWei05/gemma4-bestckpt-traces-topk128-v2-e2b-hard

Updated about 5 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-e2b-medium

Updated about 5 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-e2b-easy

Updated about 5 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-26b-easy

Updated about 5 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-12b-easy

Updated about 6 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-12b-medium

Updated about 6 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-12b-hard

Updated about 6 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-e4b-easy

Updated about 6 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-e4b-medium

Updated about 6 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-e4b-hard

Updated about 6 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-26b-medium

Updated about 6 hours ago

JWei05/gemma4-bestckpt-traces-topk128-v2-26b-hard

Updated about 6 hours ago

JWei05/DeepScaleR-Easy-Medium-Hard-Gemma-26B-PT-10k

Viewer • Updated 19 days ago • 9.9k • 281

JWei05/Nemotron-Math-v2-Medium-10k

Viewer • Updated 24 days ago • 10.5k • 136

JWei05/DeepScaleR-Medium-20k

Viewer • Updated Aug 1 • 20k • 94

JWei05/DeepScaleR-Easy-10k

Viewer • Updated Aug 1 • 10k • 107

JWei05/gemma4-e2b-base-topk128-hf-overlay-v128-seed42

Viewer • Updated Aug 1 • 48.7k • 317

JWei05/gemma4-e4b-rl100-hf-bf16-sdpa-topk128-overlay

Viewer • Updated Aug 1 • 49.6k • 276

JWei05/gemma4-e4b-rl100-topk128-traces

Updated Jul 31 • 331

JWei05/gemma4-e2b-base-topk128-traces

Updated Jul 31 • 827

JWei05/Nemotron-Math-v2-10k

Viewer • Updated Jul 27 • 10k • 41

JWei05/DeepScaleR-10k-easy

Viewer • Updated Jul 27 • 10k • 16

JWei05/DeepScaleR-4of4-strict-RL

Viewer • Updated Jul 22 • 12.9k • 25

JWei05/DeepScaleR-4of4-RL

Viewer • Updated Jul 22 • 13.6k • 25

JWei05/DeepScaleR-RL

Viewer • Updated Jul 21 • 43.5k • 8

JWei05/DAPO-Gemma3-1B-PT-DAPO-17.4k

Viewer • Updated Jul 20 • 277k • 29

JWei05/Polaris-Qwen3-4B-Instruct-2507-Traces-12k

Viewer • Updated Jul 10 • 12.2k • 9

JWei05/DeepScaleR-Qwen2.5-3B-Instruct-5k

Viewer • Updated Jul 8 • 5k • 8

JWei05/Polaris-Qwen3-8B-Traces-5k

Viewer • Updated Jun 19 • 10k • 9

JWei05/Polaris-hard-w-solutions-24209

Viewer • Updated Jun 16 • 24.2k • 28