Skywork/Skywork-Reward-Preference-80K-v0.2
Viewer
• Updated
• 77k • 356 • 63
Skywork-Reward-Data-Collection
Open-source preference datasets used to train the Skywork reward model series
Note The decontaminated version of Skywork-Reward-Preference-80K-v0.1
Skywork/Skywork-Reward-Preference-80K-v0.1
Viewer • Updated • 82k • 94 • 45Note A curated preference dataset used to train Skywork-Reward-Gemma-2-27B and Skywork-Reward-Llama-3.1-8B
-
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 14.5k • 439 -
NCSOFT/offsetbias
Viewer • Updated • 8.5k • 53 • 24 -
allenai/wildguardmix
Viewer • Updated • 88.5k • 5.04k • 61 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 300 • 221 -
Magpie-Align/Magpie-Llama-3.1-Pro-DPO-100K-v0.1
Viewer • Updated • 100k • 107 • 6 -
Magpie-Align/Magpie-Pro-DPO-100K-v0.1
Viewer • Updated • 100k • 63 • 9 -
Magpie-Align/Magpie-Air-DPO-100K-v0.1
Viewer • Updated • 100k • 42 • 4 -
chrisliu298/helpsteer2-standard
Viewer • Updated • 7.22k • 23 -
chrisliu298/offsetbias-standard
Viewer • Updated • 8.5k • 10 -
chrisliu298/wildguard-adv-standard
Viewer • Updated • 8.96k • 7 • 1 -
chrisliu298/magpie-ultra-standard
Viewer • Updated • 50k • 4 -
chrisliu298/magpie-pro-llama3.1-standard
Viewer • Updated • 98k • 3 -
chrisliu298/magpie-pro-standard
Viewer • Updated • 98k • 20 -
chrisliu298/magpie-air-standard
Viewer • Updated • 98k • 9