├── .gitignore ├── LICENSE ├── README.md ├── index.html ├── src ├── README.md ├── data │ └── math │ │ └── train │ │ ├── data-00000-of-00001.arrow │ │ ├── dataset_info.json │ │ └── state.json ├── example │ ├── case1.pdf │ ├── case2.pdf │ └── demo.ipynb ├── prm_evaluation │ ├── genprm_inference.py │ ├── policy_refine.py │ └── prm_evaluate.py ├── rationale_generation │ └── process.py ├── requirements.txt ├── reward_generation │ ├── math_shepherd_ray.py │ ├── math_shepherd_utils.py │ ├── mt_score_generate.sh │ └── steps_generate.sh └── utils │ ├── base_model_worker.py │ ├── grader.py │ ├── llm_utils.py │ ├── parse_utils.py │ ├── split_dataset.py │ ├── util.py │ └── vllm_worker.py └── static ├── css ├── bulma-carousel.min.css ├── bulma-slider.min.css ├── bulma.css.map.txt ├── bulma.min.css ├── fontawesome.all.min.css └── index.css ├── images ├── abla_component.png ├── abla_data_size.png ├── abla_label.png ├── abla_label_maj8.png ├── abla_model_size.png ├── all_processbench.png ├── comparison.png ├── critic.png ├── fig_head.png ├── framework2.png ├── main_bon.png └── main_processbench.png ├── js ├── bulma-carousel.js ├── bulma-carousel.min.js ├── bulma-slider.js ├── bulma-slider.min.js ├── fontawesome.all.min.js └── index.js └── paper.pdf /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/README.md -------------------------------------------------------------------------------- /index.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/index.html -------------------------------------------------------------------------------- /src/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/README.md -------------------------------------------------------------------------------- /src/data/math/train/data-00000-of-00001.arrow: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/data/math/train/data-00000-of-00001.arrow -------------------------------------------------------------------------------- /src/data/math/train/dataset_info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/data/math/train/dataset_info.json -------------------------------------------------------------------------------- /src/data/math/train/state.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/data/math/train/state.json -------------------------------------------------------------------------------- /src/example/case1.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/example/case1.pdf -------------------------------------------------------------------------------- /src/example/case2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/example/case2.pdf -------------------------------------------------------------------------------- /src/example/demo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/example/demo.ipynb -------------------------------------------------------------------------------- /src/prm_evaluation/genprm_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/prm_evaluation/genprm_inference.py -------------------------------------------------------------------------------- /src/prm_evaluation/policy_refine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/prm_evaluation/policy_refine.py -------------------------------------------------------------------------------- /src/prm_evaluation/prm_evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/prm_evaluation/prm_evaluate.py -------------------------------------------------------------------------------- /src/rationale_generation/process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/rationale_generation/process.py -------------------------------------------------------------------------------- /src/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/requirements.txt -------------------------------------------------------------------------------- /src/reward_generation/math_shepherd_ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/reward_generation/math_shepherd_ray.py -------------------------------------------------------------------------------- /src/reward_generation/math_shepherd_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/reward_generation/math_shepherd_utils.py -------------------------------------------------------------------------------- /src/reward_generation/mt_score_generate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/reward_generation/mt_score_generate.sh -------------------------------------------------------------------------------- /src/reward_generation/steps_generate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/reward_generation/steps_generate.sh -------------------------------------------------------------------------------- /src/utils/base_model_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/utils/base_model_worker.py -------------------------------------------------------------------------------- /src/utils/grader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/utils/grader.py -------------------------------------------------------------------------------- /src/utils/llm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/utils/llm_utils.py -------------------------------------------------------------------------------- /src/utils/parse_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/utils/parse_utils.py -------------------------------------------------------------------------------- /src/utils/split_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/utils/split_dataset.py -------------------------------------------------------------------------------- /src/utils/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/utils/util.py -------------------------------------------------------------------------------- /src/utils/vllm_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/src/utils/vllm_worker.py -------------------------------------------------------------------------------- /static/css/bulma-carousel.min.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/css/bulma-carousel.min.css -------------------------------------------------------------------------------- /static/css/bulma-slider.min.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/css/bulma-slider.min.css -------------------------------------------------------------------------------- /static/css/bulma.css.map.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/css/bulma.css.map.txt -------------------------------------------------------------------------------- /static/css/bulma.min.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/css/bulma.min.css -------------------------------------------------------------------------------- /static/css/fontawesome.all.min.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/css/fontawesome.all.min.css -------------------------------------------------------------------------------- /static/css/index.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/css/index.css -------------------------------------------------------------------------------- /static/images/abla_component.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/abla_component.png -------------------------------------------------------------------------------- /static/images/abla_data_size.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/abla_data_size.png -------------------------------------------------------------------------------- /static/images/abla_label.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/abla_label.png -------------------------------------------------------------------------------- /static/images/abla_label_maj8.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/abla_label_maj8.png -------------------------------------------------------------------------------- /static/images/abla_model_size.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/abla_model_size.png -------------------------------------------------------------------------------- /static/images/all_processbench.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/all_processbench.png -------------------------------------------------------------------------------- /static/images/comparison.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/comparison.png -------------------------------------------------------------------------------- /static/images/critic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/critic.png -------------------------------------------------------------------------------- /static/images/fig_head.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/fig_head.png -------------------------------------------------------------------------------- /static/images/framework2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/framework2.png -------------------------------------------------------------------------------- /static/images/main_bon.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/main_bon.png -------------------------------------------------------------------------------- /static/images/main_processbench.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/images/main_processbench.png -------------------------------------------------------------------------------- /static/js/bulma-carousel.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/js/bulma-carousel.js -------------------------------------------------------------------------------- /static/js/bulma-carousel.min.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/js/bulma-carousel.min.js -------------------------------------------------------------------------------- /static/js/bulma-slider.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/js/bulma-slider.js -------------------------------------------------------------------------------- /static/js/bulma-slider.min.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/js/bulma-slider.min.js -------------------------------------------------------------------------------- /static/js/fontawesome.all.min.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/js/fontawesome.all.min.js -------------------------------------------------------------------------------- /static/js/index.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/js/index.js -------------------------------------------------------------------------------- /static/paper.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RyanLiu112/GenPRM/HEAD/static/paper.pdf --------------------------------------------------------------------------------