simsun131
/

alpacafarm_ppo_lora

Model card Files Files and versions Community

alpacafarm_ppo_lora / README.md

simsun131's picture

Update README.md

e61eec9 about 1 year ago

|

141 Bytes

metadata

license: apache-2.0

A LoRA-based implementation of AlpacaFarm RLHF PPO

More details in https://github.com/SimengSun/alpaca_farm_lora