Jason Wei's picture

Jason Wei

JWei05

·

AI & ML interests

RL, LLMs, DL Theory

Recent Activity

updated a model about 13 hours ago

JWei05/gemma3-12b-pt-off-policy-distilled-from-27bptw20-step80

published a model about 13 hours ago

JWei05/gemma3-12b-pt-off-policy-distilled-from-27bptw20-step80

updated a model about 13 hours ago

JWei05/gemma3-4b-pt-off-policy-distilled-from-27bptw20-step80

View all activity

Organizations

JWei05 's models 13

JWei05/gemma3-12b-pt-off-policy-distilled-from-27bptw20-step80

Updated about 8 hours ago

JWei05/gemma3-4b-pt-off-policy-distilled-from-27bptw20-step80

Updated about 13 hours ago

JWei05/dapo-gemma3-27b-pt-warmup20

Updated about 14 hours ago

JWei05/dapo-gemma3-27b-it-warmup20

Updated 2 days ago

JWei05/gemma3-12b-it-off-policy-distilled-from-gemma4-31b

Updated 2 days ago

JWei05/gemma3-4b-it-off-policy-distilled-from-gemma4-31b

Updated 2 days ago

JWei05/gemma3-12b-pt-off-policy-distilled-from-dapo27b

Updated 2 days ago

JWei05/gemma3-4b-pt-off-policy-distilled-from-dapo27b

Updated 2 days ago

JWei05/gemma3-12b-it-off-policy-distilled-from-dapo27b-correct

Updated 3 days ago

JWei05/gemma3-4b-it-off-policy-distilled-from-dapo27b-correct

Updated 3 days ago

JWei05/gemma3-12b-it-off-policy-distilled-from-dapo27b

13B • Updated 3 days ago • 6

JWei05/gemma3-4b-it-off-policy-distilled-from-dapo27b

5B • Updated 3 days ago • 8

JWei05/dapo-gemma3-27b-it

Updated 4 days ago