-
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-adult
Viewer • Updated • 1k -
MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-adult
Viewer • Updated • 1k • 2 -
MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-child
Viewer • Updated • 1k -
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-child
Viewer • Updated • 1k
Michał Wiliński
MWilinski
AI & ML interests
Machine Learning, Reinforcement Learning
Recent Activity
updated
a collection
about 9 hours ago
irl-alignment-5.1-expert
updated
a dataset
about 9 hours ago
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-child
published
a dataset
about 9 hours ago
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-child
Organizations
-
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-adult
Viewer • Updated • 1k -
MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-adult
Viewer • Updated • 1k • 2 -
MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-child
Viewer • Updated • 1k -
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-child
Viewer • Updated • 1k
models
0
None public yet
datasets
12
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-child
Viewer
•
Updated
•
1k
MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-child
Viewer
•
Updated
•
1k
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-adult
Viewer
•
Updated
•
1k
MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-adult
Viewer
•
Updated
•
1k
•
2
MWilinski/hh-rlhf-harmless-base
Viewer
•
Updated
•
44.8k
•
23
MWilinski/hh-rlhf-helpful-base
Viewer
•
Updated
•
46.2k
•
32
MWilinski/hh-rlhf-helpful-online
Viewer
•
Updated
•
23.1k
•
23
MWilinski/hh-rlhf-helpful-rejection-sampled
Viewer
•
Updated
•
55.2k
•
16
MWilinski/hapt
Updated
•
219
MWilinski/cv_project1
Viewer
•
Updated
•
3
•
3