├── README.md ├── configs └── zero3.yaml ├── requirements.txt ├── setup.sh ├── src └── train_gsm8k.py └── train_llama_8b.sh /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minosvasilias/simple_grpo/HEAD/README.md -------------------------------------------------------------------------------- /configs/zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minosvasilias/simple_grpo/HEAD/configs/zero3.yaml -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minosvasilias/simple_grpo/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minosvasilias/simple_grpo/HEAD/setup.sh -------------------------------------------------------------------------------- /src/train_gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minosvasilias/simple_grpo/HEAD/src/train_gsm8k.py -------------------------------------------------------------------------------- /train_llama_8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minosvasilias/simple_grpo/HEAD/train_llama_8b.sh --------------------------------------------------------------------------------