Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
trl-lib
's Collections
Preference datasets
Stepwise supervision datasets
Prompt-completion datasets
Prompt-only datasets
Unpaired preference datasets
Comparing DPO with IPO and KTO
Online-DPO
Unpaired preference datasets
updated
Jan 8
Upvote
-
trl-lib/ultrafeedback-gpt-3.5-turbo-helpfulness
Viewer
•
Updated
Jan 8
•
16.6k
•
181
•
2
trl-lib/kto-mix-14k
Viewer
•
Updated
Mar 25, 2024
•
15k
•
224
•
9
Upvote
-
Share collection
View history
Collection guide
Browse collections
