Skywork/Skywork-Reward-Preference-80K-v0.2
Viewer
•
Updated
•
77k
•
1.36k
•
16
Open-source preference datasets used to train the Skywork reward model series
Note The decontaminated version of Skywork-Reward-Preference-80K-v0.1
Note A curated preference dataset used to train Skywork-Reward-Gemma-2-27B and Skywork-Reward-Llama-3.1-8B