├── .gitignore ├── ACKNOWLEDGEMENTS ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── LICENSE ├── README.md ├── figs ├── logos.png ├── pipeline.png └── teaser.png ├── inference_demo.py ├── recipes ├── accelerate_configs │ ├── ddp.yaml │ ├── fsdp.yaml │ ├── zero2.yaml │ └── zero3.yaml ├── config_coupled_code.yaml └── process_data.py ├── run.sh ├── setup.py ├── src └── open_r1 │ ├── configs.py │ ├── coupled_grpo.py │ ├── grpo.py │ ├── rewards.py │ └── utils │ ├── code_providers.py │ └── model_utils.py └── tests └── test_code_reward.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/.gitignore -------------------------------------------------------------------------------- /ACKNOWLEDGEMENTS: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/ACKNOWLEDGEMENTS -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/README.md -------------------------------------------------------------------------------- /figs/logos.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/figs/logos.png -------------------------------------------------------------------------------- /figs/pipeline.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/figs/pipeline.png -------------------------------------------------------------------------------- /figs/teaser.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/figs/teaser.png -------------------------------------------------------------------------------- /inference_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/inference_demo.py -------------------------------------------------------------------------------- /recipes/accelerate_configs/ddp.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/recipes/accelerate_configs/ddp.yaml -------------------------------------------------------------------------------- /recipes/accelerate_configs/fsdp.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/recipes/accelerate_configs/fsdp.yaml -------------------------------------------------------------------------------- /recipes/accelerate_configs/zero2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/recipes/accelerate_configs/zero2.yaml -------------------------------------------------------------------------------- /recipes/accelerate_configs/zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/recipes/accelerate_configs/zero3.yaml -------------------------------------------------------------------------------- /recipes/config_coupled_code.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/recipes/config_coupled_code.yaml -------------------------------------------------------------------------------- /recipes/process_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/recipes/process_data.py -------------------------------------------------------------------------------- /run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/run.sh -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/setup.py -------------------------------------------------------------------------------- /src/open_r1/configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/src/open_r1/configs.py -------------------------------------------------------------------------------- /src/open_r1/coupled_grpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/src/open_r1/coupled_grpo.py -------------------------------------------------------------------------------- /src/open_r1/grpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/src/open_r1/grpo.py -------------------------------------------------------------------------------- /src/open_r1/rewards.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/src/open_r1/rewards.py -------------------------------------------------------------------------------- /src/open_r1/utils/code_providers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/src/open_r1/utils/code_providers.py -------------------------------------------------------------------------------- /src/open_r1/utils/model_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/src/open_r1/utils/model_utils.py -------------------------------------------------------------------------------- /tests/test_code_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/apple/ml-diffucoder/HEAD/tests/test_code_reward.py --------------------------------------------------------------------------------