├── README.md ├── rloo_sentiment.py └── trl └── trainer ├── rloo_config.py ├── rloo_trainer.py └── utils.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rycolab/kl-rb/HEAD/README.md -------------------------------------------------------------------------------- /rloo_sentiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rycolab/kl-rb/HEAD/rloo_sentiment.py -------------------------------------------------------------------------------- /trl/trainer/rloo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rycolab/kl-rb/HEAD/trl/trainer/rloo_config.py -------------------------------------------------------------------------------- /trl/trainer/rloo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rycolab/kl-rb/HEAD/trl/trainer/rloo_trainer.py -------------------------------------------------------------------------------- /trl/trainer/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rycolab/kl-rb/HEAD/trl/trainer/utils.py --------------------------------------------------------------------------------