Jason Wei PRO

JWei05

·

AI & ML interests

RL, LLMs, DL Theory

Recent Activity

updated a dataset 2 days ago

JWei05/DeepScaleR-Easy-Medium-Hard-Qwen3-30B-A3B-Base-10k

published a dataset 2 days ago

JWei05/DeepScaleR-Easy-Medium-Hard-Qwen3-30B-A3B-Base-10k

updated a model 20 days ago

JWei05/easy10k_g16_mb64_2gpu_x4es_nostd_seed44

View all activity

Organizations

JWei05 's models 95

JWei05/DAPO-gemma4-26b-a4b-PT-DeepScaleR-gemma26b-hard-seed42-teacher-step180

JWei05/DAPO-gemma4-26b-a4b-PT-DeepScaleR-gemma26b-medium-seed42-26b-bands-es5

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-gemma26b-hard-seed42-local2gpu

Updated Sep 4 • 1

JWei05/DAPO-gemma4-26b-a4b-PT-DeepScaleR-gemma26b-hard-seed42

JWei05/DAPO-gemma4-26b-a4b-PT-DeepScaleR-gemma26b-easy-seed42-26b-bands-es5

JWei05/DAPO-gemma4-12b-PT-DeepScaleR-gemma26b-hard-seed42-26b-bands-es5

JWei05/DAPO-gemma4-12b-PT-DeepScaleR-gemma26b-medium-seed42-26b-bands-es5

JWei05/DAPO-gemma4-12b-PT-DeepScaleR-gemma26b-easy-seed42-26b-bands-es5

JWei05/DAPO-gemma4-e4b-PT-DeepScaleR-gemma26b-hard-seed42-26b-bands-es5

JWei05/DAPO-gemma4-e4b-PT-DeepScaleR-gemma26b-medium-seed42-26b-bands-es5

JWei05/DAPO-gemma4-e4b-PT-DeepScaleR-gemma26b-easy-seed42-26b-bands-es5

JWei05/gemma-4-26B-A4B-DeepScaleR-medium-s42-fullckpt-step90

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-gemma26b-easy-seed42-local2gpu

JWei05/gemma-4-26B-A4B-DeepScaleR-hard-s42-fullckpt-step47

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-gemma26b-medium-seed42-26b-bands-es5

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-gemma26b-easy-seed42-26b-bands-es5

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-medium20k-seed43-8k

JWei05/DAPO-gemma4-e4b-PT-DeepScaleR-medium20k-seed43-8k

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-easy10k-seed43-8k

JWei05/DAPO-gemma4-e4b-PT-DeepScaleR-easy10k-seed43-8k

JWei05/DAPO-gemma4-12b-PT-DeepScaleR-medium20k-seed42-8k

JWei05/DAPO-gemma4-12b-PT-DeepScaleR-medium20k-seed42-8k-medium-only-20260806

JWei05/DAPO-gemma4-e4b-PT-DeepScaleR-medium20k-seed42-8k-medium-only-20260806

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-easy10k-seed42-8k-cont300-plus100

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-easy10k-seed42-8k-cont200-plus100

JWei05/DAPO-gemma4-e4b-PT-DeepScaleR-easy10k-seed42-8k

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-easy10k-seed42-8k

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-medium20k-seed42-8k

JWei05/gemma4-e2b-base-to-e4b-topk128-distill

Text Generation • 9B • Updated Aug 1 • 17

JWei05/gemma4-e4b-rl100-to-e2b-topk128-distill