wzhouad/Llama3-Instruct-8B-WPO-FP
Text Generation • 8B • Updated • 7
WPO
Models and datasets in paper "WPO: Enhancing RLHF with Weighted Preference Optimization".
-
-
wzhouad/Llama3-Instruct-8B-WPO-HB
Text Generation • 8B • Updated • 8 • 1 -
wzhouad/zephyr-7B-WPO-FP
Text Generation • 7B • Updated • 12 -
wzhouad/zephyr-7B-WPO-HB
Text Generation • 7B • Updated • 7 -
wzhouad/Llama3-Instruct-8B-WPO-HB-v2
Text Generation • 8B • Updated • 9 • 5 -
wzhouad/gemma-2-9b-it-WPO-FP
Text Generation • 9B • Updated • 7 -
wzhouad/gemma-2-9b-it-WPO-HB
Text Generation • 9B • Updated • 19 • 34 -
wzhouad/zephyr-ultrafeedback-hybrid
Viewer • Updated • 64.7k • 185 • 2 -
wzhouad/gemma-2-ultrafeedback-hybrid
Viewer • Updated • 61.6k • 97 • 8 -
wzhouad/llama3-ultrafeedback-hybrid
Viewer • Updated • 64.5k • 119 • 2 -
wzhouad/llama3-ultrafeedback-hybrid-v2
Viewer • Updated • 64.5k • 66 • 5