Michał Wiliński's picture

In a Training Loop 🔄

Michał Wiliński

MWilinski

·

https://michal-wilinski.com

AI & ML interests

Machine Learning, Reinforcement Learning

Recent Activity

updated a model 1 minute ago

MWilinski/qwen2.5-3b-dpo-irl

published a model 1 minute ago

MWilinski/qwen2.5-3b-dpo-irl

updated a model 2 minutes ago

MWilinski/qwen2.5-3b-sft-irl

View all activity

Organizations

MWilinski 's models 6

MWilinski/qwen2.5-3b-dpo-irl

Updated 1 minute ago

MWilinski/qwen2.5-3b-sft-irl

Updated 3 minutes ago

MWilinski/qwen2.5-3b-gail

Updated 20 days ago

MWilinski/dro-v-qwen3-1.7b-paperlike

MWilinski/dro-qwen3-1.7b-full-fixed-tau

MWilinski/dro-qwen3-1.7b-full