├── .DS_Store ├── .gitignore ├── README.md ├── RM ├── inference.sh ├── inference_job.sh ├── job_orm.sh ├── job_prm.sh ├── process_reward_modeling_pointwise.py ├── reward_model_inference.py ├── reward_model_inference_MATH.py ├── reward_modeling_pointwise.py ├── run_orm.sh └── run_prm.sh ├── config ├── zero2_config_30b.json └── zero2_config_65b.json ├── eval.py ├── evaluation ├── eval_gsm8k.py ├── eval_math.py ├── meta_eval.py └── util.py ├── figs ├── convergence.png ├── data.png ├── errors.png ├── idea.png ├── results.png ├── scale.png └── train.png ├── requirements.txt ├── single_inference_7b_13b.py ├── test_7b_13b.sh ├── test_dir.sh ├── test_text_orm.py ├── train_reward.py └── train_reward_7b.sh /.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/.DS_Store -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/README.md -------------------------------------------------------------------------------- /RM/inference.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/RM/inference.sh -------------------------------------------------------------------------------- /RM/inference_job.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/RM/inference_job.sh -------------------------------------------------------------------------------- /RM/job_orm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/RM/job_orm.sh -------------------------------------------------------------------------------- /RM/job_prm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/RM/job_prm.sh -------------------------------------------------------------------------------- /RM/process_reward_modeling_pointwise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/RM/process_reward_modeling_pointwise.py -------------------------------------------------------------------------------- /RM/reward_model_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/RM/reward_model_inference.py -------------------------------------------------------------------------------- /RM/reward_model_inference_MATH.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/RM/reward_model_inference_MATH.py -------------------------------------------------------------------------------- /RM/reward_modeling_pointwise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/RM/reward_modeling_pointwise.py -------------------------------------------------------------------------------- /RM/run_orm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/RM/run_orm.sh -------------------------------------------------------------------------------- /RM/run_prm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/RM/run_prm.sh -------------------------------------------------------------------------------- /config/zero2_config_30b.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/config/zero2_config_30b.json -------------------------------------------------------------------------------- /config/zero2_config_65b.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/config/zero2_config_65b.json -------------------------------------------------------------------------------- /eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/eval.py -------------------------------------------------------------------------------- /evaluation/eval_gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/evaluation/eval_gsm8k.py -------------------------------------------------------------------------------- /evaluation/eval_math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/evaluation/eval_math.py -------------------------------------------------------------------------------- /evaluation/meta_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/evaluation/meta_eval.py -------------------------------------------------------------------------------- /evaluation/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/evaluation/util.py -------------------------------------------------------------------------------- /figs/convergence.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/figs/convergence.png -------------------------------------------------------------------------------- /figs/data.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/figs/data.png -------------------------------------------------------------------------------- /figs/errors.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/figs/errors.png -------------------------------------------------------------------------------- /figs/idea.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/figs/idea.png -------------------------------------------------------------------------------- /figs/results.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/figs/results.png -------------------------------------------------------------------------------- /figs/scale.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/figs/scale.png -------------------------------------------------------------------------------- /figs/train.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/figs/train.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/requirements.txt -------------------------------------------------------------------------------- /single_inference_7b_13b.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/single_inference_7b_13b.py -------------------------------------------------------------------------------- /test_7b_13b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/test_7b_13b.sh -------------------------------------------------------------------------------- /test_dir.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/test_dir.sh -------------------------------------------------------------------------------- /test_text_orm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/test_text_orm.py -------------------------------------------------------------------------------- /train_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/train_reward.py -------------------------------------------------------------------------------- /train_reward_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KbsdJames/MATH-Minos/HEAD/train_reward_7b.sh --------------------------------------------------------------------------------