Aosong Feng PRO

afeng 's models 236

Sort:  Recently updated

afeng/qwen3_8b_rollout12_step-100

8B • Updated 5 days ago • 15

afeng/qwen3_8b_default_step-100

8B • Updated 5 days ago • 16

afeng/qwen3_4b_rollout12_step-100

4B • Updated 5 days ago • 17

afeng/qwen3_4b_no_uncertain_step-300

4B • Updated 5 days ago • 16

afeng/qwen3_4b_default_step-100

4B • Updated 5 days ago • 21

afeng/qwen3_4b_rollout4_step-500

4B • Updated 5 days ago • 9

afeng/qwen3_4b_rollout4_step-400

4B • Updated 5 days ago • 9

afeng/qwen3_4b_no_uncertain_step-200

4B • Updated 5 days ago • 8

afeng/qwen3_4b_rollout4_step-300

4B • Updated 5 days ago • 6

afeng/qwen3_4b_no_uncertain_step-100

4B • Updated 5 days ago • 8

afeng/fin_text_qa_qwen3_8b_step-3

8B • Updated 5 days ago • 12

afeng/fin_text_qa_qwen3_8b_step-2

8B • Updated 5 days ago • 8

afeng/fin-ckpts

Updated 30 days ago

afeng/math_intuitor_qwen25-14b

15B • Updated Jun 30, 2025 • 1

afeng/math_grpo_qwen25-14b

15B • Updated Jun 29, 2025

afeng/math_grpo_qwen25-7b

8B • Updated Jun 29, 2025

afeng/math_intuitor_qwen25-7b

8B • Updated Jun 29, 2025

afeng/Qwen2.5-SPO-7B-22

Text Generation • 8B • Updated May 23, 2025

afeng/Qwen2.5-GRPO-7B-22

Text Generation • 8B • Updated May 22, 2025 • 3

afeng/Qwen2.5-14B-GRPO

Text Generation • 15B • Updated May 20, 2025

afeng/Qwen2.5-14B-SPO

Text Generation • 15B • Updated May 19, 2025

afeng/Qwen2.5-7B-SPO-3e6

Text Generation • 8B • Updated May 19, 2025

afeng/Qwen2.5-7B-SPO

Text Generation • 8B • Updated May 19, 2025

afeng/Qwen2.5-GRPO-7B-5e7

Text Generation • 8B • Updated May 15, 2025

afeng/Qwen2.5-MJ-GRPO-3B

Text Generation • 3B • Updated May 13, 2025

afeng/Qwen2.5-SPO-3B-kl0

Text Generation • 3B • Updated May 13, 2025