Michał Wiliński's picture

In a Training Loop 🔄

Michał Wiliński

MWilinski

·

https://michal-wilinski.com

AI & ML interests

Machine Learning, Reinforcement Learning

Recent Activity

published a model about 2 hours ago

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

updated a dataset 1 day ago

MWilinski/hh-rlhf-irl

updated a dataset 2 days ago

MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-policy

View all activity

Organizations

MWilinski 's datasets 17

MWilinski/hh-rlhf-irl

Viewer • Updated 1 day ago • 10k • 81

MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-policy

Viewer • Updated 2 days ago • 2k

MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-policy

Viewer • Updated 2 days ago • 2k

MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-child

Viewer • Updated 2 days ago • 1.5k • 110

MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-adult

Viewer • Updated 2 days ago • 1.5k • 100

MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-adult

Viewer • Updated 2 days ago • 1.5k • 102

MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-child

Viewer • Updated 2 days ago • 1.5k • 109

MWilinski/hh-rlhf-harmless-base-rollouts-gpt-oss-20b

Viewer • Updated 2 days ago • 1.2k • 120

MWilinski/hh-rlhf-helpful-base-rollouts-gpt-oss-20b

Viewer • Updated 28 days ago • 1.2k • 117

MWilinski/hh-rlhf-harmless-base

Viewer • Updated Nov 5, 2025 • 44.8k • 47

MWilinski/hh-rlhf-helpful-base

Viewer • Updated Nov 5, 2025 • 46.2k • 47

MWilinski/hh-rlhf-helpful-online

Viewer • Updated Nov 5, 2025 • 23.1k • 23

MWilinski/hh-rlhf-helpful-rejection-sampled

Viewer • Updated Nov 5, 2025 • 55.2k • 18

MWilinski/hapt

Updated Apr 15, 2025 • 7

MWilinski/cv_project1

Viewer • Updated Nov 29, 2023 • 3 • 9

MWilinski/cats_dogs_cv_labs

Viewer • Updated Nov 16, 2023 • 21 • 5

MWilinski/snips_slu_v1.0

Viewer • Updated May 22, 2023 • 5.89k • 20 • 1