Zhemin Huang

zheminh 's models 83

Sort:  Recently updated

zheminh/grpo-0612-verl-math-fmt-with-acc-strict-step08

8B • Updated Jun 12, 2025 • 1

zheminh/grpo-0609-verl-math-step09

8B • Updated Jun 10, 2025 • 2

zheminh/grpo-0604-step15

8B • Updated Jun 5, 2025 • 2

zheminh/grpo-0602-verl-step12

8B • Updated Jun 3, 2025 • 2

zheminh/grpo-0531-ckpt30

8B • Updated Jun 1, 2025 • 1

zheminh/grpo-0531-ckpt150

8B • Updated Jun 1, 2025

zheminh/grpo-0529-ckpt60

8B • Updated May 30, 2025 • 2

zheminh/grpo-0529-ckpt30

8B • Updated May 30, 2025 • 2

zheminh/grpo-0529-length-comparison-ckpt90

8B • Updated May 29, 2025

zheminh/grpo-0529-ckpt90

8B • Updated May 29, 2025 • 1

zheminh/grpo-0527-ckpt120

8B • Updated May 28, 2025 • 2

zheminh/dapo-ckpt100

8B • Updated May 27, 2025

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-MATH-Olympiad-Merged-Chains-with-prompt-ckpt1200

8B • Updated May 13, 2025 • 1

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-Olympiad-Merged-Chains-ckpt1200

8B • Updated May 12, 2025 • 1

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-MATH-Olympiad-Merged-Chains-ckpt1600

8B • Updated May 12, 2025 • 1

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-MATH-Merged-Chains-ckpt700

8B • Updated May 12, 2025 • 4

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-MATH-Merged-Chains-ckpt300

8B • Updated May 12, 2025 • 2

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-Math-DAPO-ckpt240

8B • Updated May 8, 2025 • 1

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-Math-DAPO-ckpt180

8B • Updated May 8, 2025

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-Math-DAPO-ckpt210

8B • Updated May 8, 2025 • 1

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-MATH-Olympiad-ckpt1200

8B • Updated May 8, 2025

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-MATH-Olympiad-ckpt800

8B • Updated May 8, 2025 • 1

zheminh/DeepSeek-R1-Distill-Qwen-7B-DAPO-ckpt90

8B • Updated May 7, 2025 • 1

zheminh/DeepSeek-R1-Distill-Qwen-7B-RFT-R1-Distill-ckpt400

8B • Updated May 7, 2025 • 1

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-Math-ckpt600

8B • Updated May 4, 2025 • 1

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-Math-ckpt500

8B • Updated May 4, 2025

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-Math-ckpt300

8B • Updated May 4, 2025 • 1

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-Math-ckpt400

8B • Updated May 4, 2025 • 2

zheminh/DeepSeek-R1-Distill-Qwen-7B-Trajectory-Data-Math-ckpt150

8B • Updated May 4, 2025 • 1

zheminh/Qwen3-8B-Execution-Data-Math-Orig-and-Dagger-think-ckpt4800

8B • Updated May 2, 2025 • 1