🔄 In a Training Loop

Michał Wiliński

MWilinski

·

https://michal-wilinski.com

AI & ML interests

Machine Learning, Reinforcement Learning

Recent Activity

updated a model about 14 hours ago

MWilinski/gemma-3-4b-pared-helpsteer3

updated a model about 14 hours ago

MWilinski/gemma-3-4b-pared-hhrlhf

published a model about 17 hours ago

MWilinski/gemma-3-4b-pared-hhrlhf

View all activity

Organizations

MWilinski 's datasets 19

MWilinski/rlhf-irl-pirate-expert

Viewer • Updated Apr 30 • 6k • 9

MWilinski/rlhf-irl

Viewer • Updated Apr 15 • 14k • 42

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

Viewer • Updated Mar 24 • 200 • 54

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

Viewer • Updated Mar 24 • 200 • 84

MWilinski/hh-rlhf-irl

Viewer • Updated Mar 23 • 10k • 5

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

Viewer • Updated Mar 10 • 2k • 18

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

Viewer • Updated Mar 10 • 2k • 22

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

Viewer • Updated Mar 10 • 1.5k • 26

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

Viewer • Updated Mar 10 • 1.5k • 18

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

Viewer • Updated Mar 10 • 1.5k • 28

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

Viewer • Updated Mar 10 • 1.5k • 25

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

Viewer • Updated Mar 10 • 1.2k • 22

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

Viewer • Updated Feb 12 • 1.2k • 35

MWilinski/hh-rlhf-harmless-base

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

MWilinski/hh-rlhf-helpful-base

Viewer • Updated Nov 5, 2025 • 46.2k • 8

MWilinski/hapt

Updated Apr 15, 2025 • 14

MWilinski/cv_project1

Viewer • Updated Nov 29, 2023 • 3 • 14

MWilinski/cats_dogs_cv_labs

Viewer • Updated Nov 16, 2023 • 21 • 38

MWilinski/snips_slu_v1.0

Viewer • Updated May 22, 2023 • 5.89k • 33 • 1