*.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text *.ckpt filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text *.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text *.npy filter=lfs diff=lfs merge=lfs -text *.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text *.pickle filter=lfs diff=lfs merge=lfs -text *.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text *.safetensors filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text *.tar filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text deepseek-r1-distill-qwen-1.5b-grpo-concept-enhanced/tokenizer.json filter=lfs diff=lfs merge=lfs -text deepseek-r1-distill-qwen-1.5b-grpo-concept-enhanced/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text deepseek-r1-distill-qwen-1.5b-grpo-concept-enhanced/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text meta-llama-3-8b-instruct-grpo-concept-enhanced/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text meta-llama-3-8b-instruct-grpo-concept-enhanced/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2.5-math-1.5b-grpo-concept-enhanced/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2.5-math-1.5b-grpo-concept-enhanced/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/20250919_001337/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/llama-3-8b/grpo_math_outputs_verl_llama_origin_3epochs/mathevo-grpo-verl/Meta-Llama-3-8B-grpo-origin-3epochs-20250908_113235/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250919_001337/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250920_110827/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250920_110827/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250920_160615-resume/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/mathevo-grpo-verl-deepmath-concept-enhanced/deepmath-1.5b-grpo-concept-enhanced-20250920_160615-resume/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/Meta-Llama-3-8B-Instruct-20250924_170947/mathevo-grpo-verl-concept-enhanced/Meta-Llama-3-8B-Instruct-20250924_170947/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/Meta-Llama-3-8B-Instruct-20250924_170947/mathevo-grpo-verl-concept-enhanced/Meta-Llama-3-8B-Instruct-20250924_170947/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b/lora/conceptandquiz-sft/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b/lora/conceptandquiz-sft/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b/lora/conceptandquiz-sft/checkpoint-165/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b/lora/conceptandquiz-sft/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b/lora/conceptandquiz-sft/mergedsft_conceptandquiz100/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b/lora/conceptandquiz-sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-7b/lora/conceptandquiz-sft/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-7b/lora/conceptandquiz-sft/checkpoint-135/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-7b/lora/conceptandquiz-sft/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-7b/lora/conceptandquiz-sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-7b/lora/sft-2gpu/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-7b/lora/sft-2gpu/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-7b/lora/sft-2gpu/checkpoint-24/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-7b/lora/sft-2gpu/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-7b/lora/sft-2gpu/checkpoint-318/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-7b/lora/sft-2gpu/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b-grpo-concept-enhanced-20250920_110827/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b-grpo-concept-enhanced-20250920_110827/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250920_202806/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250920_202806/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/model/merged-sft-conceptandquiz/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/Qwen2.5-Math-1.5B-Instruct-20250924_015412/mathevo-grpo-verl-concept-enhanced/Qwen2.5-Math-1.5B-Instruct-20250924_015412/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/Qwen2.5-Math-1.5B-Instruct-20250924_015412/mathevo-grpo-verl-concept-enhanced/Qwen2.5-Math-1.5B-Instruct-20250924_015412/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/Qwen2.5-Math-1.5B-Instruct-20250924_015412/mathevo-grpo-verl-concept-enhanced/Qwen2.5-Math-1.5B-Instruct-20250924_015412/global_step_72/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/Qwen2.5-Math-1.5B-Instruct-20250924_015412/mathevo-grpo-verl-concept-enhanced/Qwen2.5-Math-1.5B-Instruct-20250924_015412/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b-grpo-origin-10epochs-20250918_195851/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b-grpo-origin-10epochs-20250918_195851/global_step_50/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_math_outputs_verl_top4of6_3epochs/mathevo-grpo-verl-top4of6/Qwen2-Math-7B-grpo-top4of6-3epochs-20250921_115920/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_math_outputs_verl_top4of6_3epochs/mathevo-grpo-verl-top4of6/Qwen2-Math-7B-grpo-top4of6-3epochs-20250921_115920/global_step_50/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/SFT-step24/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/QwenKL/grpo_math_outputs_verl_kl-enhanced_3epochs/mathevo-grpo-verl-kl/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/QwenKL/grpo_math_outputs_verl_kl-enhanced_3epochs/mathevo-grpo-verl-kl/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen-2-math-7b/grpo_math_outputs_verl_concept_enhanced/mathevo-grpo-verl-concept-enhanced/qwen2-math-7b-grpo-concept-enhanced-20250901_221032/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen-2-math-7b/grpo_math_outputs_verl_concept_enhanced/mathevo-grpo-verl-concept-enhanced/qwen2-math-7b-grpo-concept-enhanced-20250901_221032/global_step_50/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen-2-math-7b/grpo_math_outputs_verl_origin_3epochs/mathevo-grpo-verl/qwen2-math-7b-grpo-origin-3epochs-20250902_211422/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen-2-math-7b/grpo_math_outputs_verl_origin_3epochs/mathevo-grpo-verl/qwen2-math-7b-grpo-origin-3epochs-20250902_211422/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen-2-math-7b/grpo_math_outputs_verl_self_consistent/mathevo-grpo-verl-self-consistent/qwen2-math-7b-grpo-self-consistent/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen-2-math-7b/grpo_math_outputs_verl_self_consistent/mathevo-grpo-verl-self-consistent/qwen2-math-7b-grpo-self-consistent/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen-2-math-7b/mathevo-grpo-verl-kl/qwen2-math-7b-grpo-kl-enhanced-3epochs-20250902_225651/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen-2-math-7b/mathevo-grpo-verl-kl/qwen2-math-7b-grpo-kl-enhanced-3epochs-20250902_225651/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/merged-sft-conceptandquiz-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-1.5b-grpo-concept-enhanced-20250923_164417/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/qwen2-math-1.5b-grpo-concept-enhanced-20250923_164417/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/SFT/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/DeepMath-1.5B-20250923_225516/mathevo-grpo-verl-concept-enhanced/DeepMath-1.5B-20250923_225516/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/DeepMath-1.5B-20250923_225516/mathevo-grpo-verl-concept-enhanced/DeepMath-1.5B-20250923_225516/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/DeepMath-1.5B-20250923_225516/mathevo-grpo-verl-concept-enhanced/DeepMath-1.5B-20250923_225516/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/DeepMath-1.5B-20250923_225516/mathevo-grpo-verl-concept-enhanced/DeepMath-1.5B-20250923_225516/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2-math-7b-grpo-gpt4o-baseline-step24/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2-math-7b-grpo-gpt4o-baseline-step24/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2-math-7b-ppo-reinforce-concept-enhanced-step24/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2-math-7b-ppo-reinforce-concept-enhanced-step24/tokenizer.json filter=lfs diff=lfs merge=lfs -text mathevo-grpo-verl/qwen2-math-7b-grpo-llm-judge-origin-3epochs/global_step_12/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text mathevo-grpo-verl/qwen2-math-7b-grpo-llm-judge-origin-3epochs/global_step_12/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text global_step_12/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text global_step_12/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text mathevo-grpo-baseline/qwen2-math-7b-grpo-baseline-3epochs/global_step_12/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text mathevo-grpo-baseline/qwen2-math-7b-grpo-baseline-3epochs/global_step_12/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text