aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_all_1204_1600
31B • Updated • 3
TY.Zheng
aaabiao
AI & ML interests
None yet
Recent Activity
upvoted a paper about 17 hours ago
MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection updated a dataset 9 days ago
aaabiao/skill_100 published a dataset 9 days ago
aaabiao/skill_100Organizations
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_all_1204_1200
31B • Updated
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_all_1204_800
31B • Updated • 1
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_all_1204_400
31B • Updated • 2
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_all_1204_1815
31B • Updated • 5
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_all_1115_4000
31B • Updated • 1
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_all_1115_3000
31B • Updated
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_all_1115_2000
31B • Updated • 2
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_all_1115_5376
Updated
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_all_1115_1000
31B • Updated • 2
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_resolved_1115_1200
31B • Updated
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_resolved_1115_400
31B • Updated
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_resolved_1115_800
31B • Updated
aaabiao/Qwen3-Coder-30B-A3B-Instruct_swe_traj_train_resolved_1115_1776
31B • Updated
aaabiao/cc_sft_Qwen3-Coder-30B-A3B-Instruct-1021
31B • Updated • 1
aaabiao/qwen3_14b_think_32B_math_reject_sampling_150step_0706
15B • Updated • 1
aaabiao/qwen3_14b_no_think_32B_math_reject_sampling_150step_0706
15B • Updated • 1
aaabiao/qwen3_14b_think_32B_math_reject_sampling_150step
15B • Updated • 2
aaabiao/qwen3_14b_no_think_32B_math_reject_sampling_150step
15B • Updated • 3
aaabiao/qwen3_14b_distill_no_think_32b_5e5_150step_fix2
15B • Updated
aaabiao/verl-8B-100step-v1
8B • Updated
aaabiao/verl-4B-100step-v1
4B • Updated • 1
aaabiao/qwen3_14b_distill_no_think_32b_5e5_150step_fix
15B • Updated • 1
aaabiao/verl-14B-60step-v1
15B • Updated • 1
aaabiao/verl-14B-120step-v1
15B • Updated
aaabiao/verl-14B-40step-v1
15B • Updated • 1
aaabiao/verl-14B-100step-v1
15B • Updated • 1
aaabiao/verl-14B-20step-v1
15B • Updated • 3
aaabiao/verl-14B-80step-v1
15B • Updated • 3
aaabiao/qwen3_14b_distill_think_32b_5e5_285step
15B • Updated