├── .gitignore ├── .gitmodules ├── README.md ├── assets ├── 14B.png ├── 7B.png ├── distribution.png ├── teaser.png └── verifier.png ├── compute_score.py ├── data_preprocess.py ├── evaluation ├── eval_bbeh.py ├── eval_mmlupro.py ├── eval_supergpqa.py └── simple-evals │ ├── README.md │ ├── aime24_eval_qwen.py │ ├── aime25_eval_qwen.py │ ├── amc_eval_qwen.py │ ├── common.py │ ├── gpqa_eval_qwen.py │ ├── gsm8k_eval_qwen.py │ ├── math_eval_qwen.py │ ├── minerva_eval_qwen.py │ ├── olympiad_eval_qwen.py │ ├── run_simple_evals_qwen.py │ ├── sampler │ ├── chat_completion_sampler.py │ └── qwen_chat_completion_sampler.py │ └── types.py ├── main_ppo.py ├── tinker_scripts ├── merge_checkpoints.py └── tinker_train_general_reasoner.py ├── train_general_reasoner.sh └── verifier.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/.gitmodules -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/README.md -------------------------------------------------------------------------------- /assets/14B.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/assets/14B.png -------------------------------------------------------------------------------- /assets/7B.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/assets/7B.png -------------------------------------------------------------------------------- /assets/distribution.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/assets/distribution.png -------------------------------------------------------------------------------- /assets/teaser.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/assets/teaser.png -------------------------------------------------------------------------------- /assets/verifier.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/assets/verifier.png -------------------------------------------------------------------------------- /compute_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/compute_score.py -------------------------------------------------------------------------------- /data_preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/data_preprocess.py -------------------------------------------------------------------------------- /evaluation/eval_bbeh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/eval_bbeh.py -------------------------------------------------------------------------------- /evaluation/eval_mmlupro.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/eval_mmlupro.py -------------------------------------------------------------------------------- /evaluation/eval_supergpqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/eval_supergpqa.py -------------------------------------------------------------------------------- /evaluation/simple-evals/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/README.md -------------------------------------------------------------------------------- /evaluation/simple-evals/aime24_eval_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/aime24_eval_qwen.py -------------------------------------------------------------------------------- /evaluation/simple-evals/aime25_eval_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/aime25_eval_qwen.py -------------------------------------------------------------------------------- /evaluation/simple-evals/amc_eval_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/amc_eval_qwen.py -------------------------------------------------------------------------------- /evaluation/simple-evals/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/common.py -------------------------------------------------------------------------------- /evaluation/simple-evals/gpqa_eval_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/gpqa_eval_qwen.py -------------------------------------------------------------------------------- /evaluation/simple-evals/gsm8k_eval_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/gsm8k_eval_qwen.py -------------------------------------------------------------------------------- /evaluation/simple-evals/math_eval_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/math_eval_qwen.py -------------------------------------------------------------------------------- /evaluation/simple-evals/minerva_eval_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/minerva_eval_qwen.py -------------------------------------------------------------------------------- /evaluation/simple-evals/olympiad_eval_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/olympiad_eval_qwen.py -------------------------------------------------------------------------------- /evaluation/simple-evals/run_simple_evals_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/run_simple_evals_qwen.py -------------------------------------------------------------------------------- /evaluation/simple-evals/sampler/chat_completion_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/sampler/chat_completion_sampler.py -------------------------------------------------------------------------------- /evaluation/simple-evals/sampler/qwen_chat_completion_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/sampler/qwen_chat_completion_sampler.py -------------------------------------------------------------------------------- /evaluation/simple-evals/types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/evaluation/simple-evals/types.py -------------------------------------------------------------------------------- /main_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/main_ppo.py -------------------------------------------------------------------------------- /tinker_scripts/merge_checkpoints.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/tinker_scripts/merge_checkpoints.py -------------------------------------------------------------------------------- /tinker_scripts/tinker_train_general_reasoner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/tinker_scripts/tinker_train_general_reasoner.py -------------------------------------------------------------------------------- /train_general_reasoner.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/train_general_reasoner.sh -------------------------------------------------------------------------------- /verifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TIGER-AI-Lab/General-Reasoner/HEAD/verifier.py --------------------------------------------------------------------------------