├── .github └── workflows │ └── main.yml ├── .gitignore ├── CONTRIBUTING.md ├── LICENSE ├── MANIFEST.in ├── Makefile ├── README.md ├── nbs ├── 00-core.ipynb ├── 01-model-with-value-head.ipynb ├── 02-ppo.ipynb ├── 03_writing_prompt_reward_model_training.ipynb ├── 04_writing_prompt_supervised_baseline_training.ipynb └── 05-writing-prompts-rlhf.ipynb ├── requirements.txt ├── settings.ini └── setup.py /.github/workflows/main.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/.github/workflows/main.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/.gitignore -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/LICENSE -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/MANIFEST.in -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/README.md -------------------------------------------------------------------------------- /nbs/00-core.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/nbs/00-core.ipynb -------------------------------------------------------------------------------- /nbs/01-model-with-value-head.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/nbs/01-model-with-value-head.ipynb -------------------------------------------------------------------------------- /nbs/02-ppo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/nbs/02-ppo.ipynb -------------------------------------------------------------------------------- /nbs/03_writing_prompt_reward_model_training.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/nbs/03_writing_prompt_reward_model_training.ipynb -------------------------------------------------------------------------------- /nbs/04_writing_prompt_supervised_baseline_training.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/nbs/04_writing_prompt_supervised_baseline_training.ipynb -------------------------------------------------------------------------------- /nbs/05-writing-prompts-rlhf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/nbs/05-writing-prompts-rlhf.ipynb -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/requirements.txt -------------------------------------------------------------------------------- /settings.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/settings.ini -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anshradh/trl_custom/HEAD/setup.py --------------------------------------------------------------------------------