Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
RLHFlow
's Collections
Standard-format-preference-dataset
Mixture-of-preference-reward-modeling
RM-Bradley-Terry
PM-pair
Online RLHF
RM-Bradley-Terry
updated
Apr 29
We train the reward model as the maximum likelihood estimation of the Bradley-Terry model.
Upvote
-
sfairXC/FsfairX-LLaMA3-RM-v0.1
Text Classification
•
Updated
Apr 24
•
6.27k
•
20
hendrydong/preference_700K
Viewer
•
Updated
Apr 18
•
255
•
1
weqweasdas/RM-Mistral-7B
Text Classification
•
Updated
Mar 31
•
5.56k
•
17
weqweasdas/preference_dataset_mixture2_and_safe_pku
Viewer
•
Updated
Apr 29
•
222
•
6
weqweasdas/RM-Gemma-2B
Text Classification
•
Updated
Mar 22
•
2.5k
•
12
Upvote
-
Share collection
View history
Collection guide
Browse collections