List your company

Conversational Assistant on Preference Optimization Conversational

0.28RewardZOPrO
0.1240.16450.2050.2455Mar 5, 2025

Evaluation results

MethodLinks
ZOPrOModel=Qwen 2.5, Parameters=1.5B2025.030.28
ZOPrOModel=Gemma 2, Parameters=2.4B2025.030.13