Ctrl+K
- 20250919_001337
- DeepMath-1.5B-20250923_225516
- DeepScaleR-1.5B-Preview-20250923_225340
- Meta-Llama-3-8B-Instruct-20250924_170947
- Meta-Llama-3-8B-Instruct-Enhanced
- Qwen2.5-Math-1.5B-Instruct-20250924_015412
- QwenKL
- SFT-step24
- SFT
- actor
- deepmath-1.5b-grpo-concept-enhanced-20250920_110827
- deepmath-1.5b-grpo-origin-10epochs-20250918_195851
- deepmath-1.5b-grpo-origin-top4of6-10epochs-20250920_202806
- deepmath-1.5b
- deepseek-math-7b-grpo-concept-enhanced-20250916_200145
- deepseek_math_7b_base
- grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled
- grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs
- grpo_math_outputs_verl_deepseek_concept_enhanced
- grpo_math_outputs_verl_top4of6_3epochs
- llama-3-8b
- mathevo-grpo-verl-deepmath-concept-enhanced
- merged-sft-conceptandquiz-100
- model
- qwen-2-math-7b
- qwen2-math-1.5b-grpo-concept-enhanced-20250923_164417
- qwen2-math-7b