RM-Bradley-Terry - a RLHFlow Collection

RLHFlow 's Collections

Decision-Tree Reward Models

RLHFlow MATH Process Reward Model

Standard-format-preference-dataset

Mixture-of-preference-reward-modeling

RM-Bradley-Terry

PM-pair

RLHFLow Reward Models

RM-Bradley-Terry

updated Apr 29, 2024

We train the reward model as the maximum likelihood estimation of the Bradley-Terry model.

sfairXC/FsfairX-LLaMA3-RM-v0.1

Text Classification • 8B • Updated Oct 14, 2024 • 2.35k • 60
hendrydong/preference_700K

Viewer • Updated Sep 28, 2024 • 700k • 445 • 16
weqweasdas/RM-Mistral-7B

Text Classification • 7B • Updated Mar 31, 2024 • 450 • 23
weqweasdas/preference_dataset_mixture2_and_safe_pku

Viewer • Updated Apr 29, 2024 • 555k • 25 • 11
weqweasdas/RM-Gemma-2B

Text Classification • 3B • Updated Mar 22, 2024 • 446 • 25