Jason Wei PRO

JWei05

·

AI & ML interests

RL, LLMs, DL Theory

Recent Activity

updated a model 1 day ago

JWei05/tmax-grpo-b32-mas4x4-h200-r1

published a model 3 days ago

JWei05/tmax-grpo-b32-mas4x4-h200-r1

published a dataset 4 days ago

JWei05/olympiad-lean-geometry-combinatorics

View all activity

Organizations

JWei05 's models 96

JWei05/Distill-gemma4-e4b-base-medium-to-26b-base

JWei05/qwen2.5-3b-deepscaler-critic-priv1

3B • Updated Sep 11 • 8

JWei05/qwen2.5-3b-deepscaler-critic-priv0

3B • Updated Sep 11 • 7

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-gemma26b-easy-seed43-26b-bands-es5

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-gemma26b-medium-seed43-26b-bands-es5

JWei05/DAPO-gemma4-e4b-PT-DeepScaleR-gemma26b-medium-seed43-26b-bands-es5

JWei05/DAPO-gemma4-e4b-PT-DeepScaleR-gemma26b-easy-seed43-26b-bands-es5

JWei05/DAPO-gemma4-e2b-PT-DeepScaleR-gemma26b-hard-seed43-26b-bands-es5

JWei05/gemma4-distill-v2-e4b-hard-to-e4b-base

JWei05/gemma4-distill-v2-e4b-hard-to-e2b-base

JWei05/gemma4-distill-v2-e4b-medium-to-e4b-base

JWei05/gemma4-distill-v2-12b-medium-to-e2b-base

JWei05/gemma4-distill-v2-12b-hard-to-e2b-base

JWei05/gemma4-distill-v2-e4b-medium-to-e2b-base

JWei05/gemma4-distill-v2-e4b-easy-to-e2b-base

JWei05/Distill-gemma4-e4b-hard-to-e2b-base

JWei05/Distill-gemma4-26b-medium-to-e4b-base

JWei05/Distill-gemma4-26b-easy-to-e4b-base

JWei05/gemma4-distill-v2-e4b-easy-to-e4b-base

JWei05/Distill-gemma4-26b-hard-to-e4b-base

JWei05/Distill-gemma4-26b-hard-to-e2b-base

JWei05/gemma4-distill-v2-12b-medium-to-e4b-base

JWei05/Distill-gemma4-26b-medium-to-e2b-base

JWei05/Distill-gemma4-e2b-easy-to-e2b-base

JWei05/gemma4-distill-v2-12b-hard-to-e4b-base

JWei05/Distill-gemma4-26b-easy-to-e2b-base

JWei05/gemma4-distill-v2-12b-easy-to-e2b-base

JWei05/Distill-gemma4-e2b-hard-to-e2b-base

JWei05/Distill-gemma4-e2b-medium-to-e2b-base

JWei05/gemma4-distill-v2-12b-easy-to-e4b-base