• Hongxin Liu's avatar
    [chat] refactor model save/load logic (#3654) · 842768a1
    Hongxin Liu authored
    * [chat] strategy refactor unwrap model
    
    * [chat] strategy refactor save model
    
    * [chat] add docstr
    
    * [chat] refactor trainer save model
    
    * [chat] fix strategy typing
    
    * [chat] refactor trainer save model
    
    * [chat] update readme
    
    * [chat] fix unit test
    842768a1
train_reward_model.py 9.38 KB