wang's picture

4

wang

wzx111

·

AI & ML interests

None yet

Recent Activity

new activity 13 days ago

wzx111/Qwen3-1.7B-MATH-GDPO:Which post-training method was actually used for this model, GDPO or GRPO?

updated a dataset about 1 month ago

wzx111/MATH-lighteval-level3

published a dataset about 1 month ago

wzx111/MATH-lighteval-level3

View all activity

Organizations

spaces 2

My Argilla

好

Chatweb

models 8

wzx111/Qwen3-1.7B-GRPO-math

Updated Nov 29, 2025

wzx111/Qwen3-1.7B-Open-R1-ADPO

Text Generation • 2B • Updated Nov 23, 2025 • 1

wzx111/Qwen3-1.7B-Open-R1-GRPO-Baseline

Text Generation • 2B • Updated Nov 22, 2025 • 1

wzx111/Qwen3-1.7B-Open-R1-GRPO

2B • Updated May 14, 2025 • 2

wzx111/Qwen3-1.7B-Open-R1-GDPO-epcoh_

Text Generation • 2B • Updated May 14, 2025 • 5

wzx111/Qwen3-1.7B-MATH-GDPO-EPOCH2

Text Generation • 2B • Updated May 2, 2025 • 4

wzx111/Qwen3-1.7B-MATH-GDPO

Text Generation • 2B • Updated May 1, 2025 • 21 • 1

wzx111/Qwen2.5-1.5B-Open-R1-GRPO

Text Generation • 2B • Updated Apr 28, 2025 • 4

datasets 3

wzx111/MATH-lighteval-level3

Viewer • Updated Dec 9, 2025 • 2.72k • 8

wzx111/MATH-lighteval-level-middlehigh

Viewer • Updated Nov 24, 2025 • 5.63k • 7

wzx111/MATH-lighteval-level-middle

Viewer • Updated Nov 24, 2025 • 7.87k • 3