├── .gitignore ├── README.md ├── configs └── deepspeed_zero3.yml ├── gsm8k.py ├── plots ├── RLVR-GSM8K-Plots.png └── rlvr-banner.png ├── resources ├── __init__.py ├── examplars.py └── gsm8k_few_shot_prompts.json ├── train.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.ipynb 2 | __pycache__ 3 | *.pyc 4 | GRPO 5 | outputs 6 | wandb 7 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mohammadjafari80/GSM8K-RLVR/HEAD/README.md -------------------------------------------------------------------------------- /configs/deepspeed_zero3.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mohammadjafari80/GSM8K-RLVR/HEAD/configs/deepspeed_zero3.yml -------------------------------------------------------------------------------- /gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mohammadjafari80/GSM8K-RLVR/HEAD/gsm8k.py -------------------------------------------------------------------------------- /plots/RLVR-GSM8K-Plots.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mohammadjafari80/GSM8K-RLVR/HEAD/plots/RLVR-GSM8K-Plots.png -------------------------------------------------------------------------------- /plots/rlvr-banner.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mohammadjafari80/GSM8K-RLVR/HEAD/plots/rlvr-banner.png -------------------------------------------------------------------------------- /resources/__init__.py: -------------------------------------------------------------------------------- 1 | from resources.examplars import EXAMPLARS -------------------------------------------------------------------------------- /resources/examplars.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mohammadjafari80/GSM8K-RLVR/HEAD/resources/examplars.py -------------------------------------------------------------------------------- /resources/gsm8k_few_shot_prompts.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mohammadjafari80/GSM8K-RLVR/HEAD/resources/gsm8k_few_shot_prompts.json -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mohammadjafari80/GSM8K-RLVR/HEAD/train.py -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mohammadjafari80/GSM8K-RLVR/HEAD/utils.py --------------------------------------------------------------------------------