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 • Updated Oct 14, 2024 • 3.99k • 57
hendrydong/preference_700K

Viewer • Updated Sep 28, 2024 • 700k • 317 • 15
weqweasdas/RM-Mistral-7B

Text Classification • Updated Mar 31, 2024 • 375 • 23
weqweasdas/preference_dataset_mixture2_and_safe_pku

Viewer • Updated Apr 29, 2024 • 555k • 101 • 11
weqweasdas/RM-Gemma-2B

Text Classification • Updated Mar 22, 2024 • 1.42k • 25