Shuai Zhang

z369217411's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 1 day ago

TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning

Paper • 2610.07043 • Published 5 days ago • 39

upvoted a paper 1 day ago

TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning

Paper • 2610.07043 • Published 5 days ago • 39

authored a paper 1 day ago

A Practical Chinese Dependency Parser Based on A Large-scale Dataset

Paper • 2009.00901 • Published Sep 3, 2020

updated a model 2 months ago

z369217411/Qwen3-30B-A3B-GRPO-W4A4-NoOverlong-Step800

Reinforcement Learning • 31B • Updated Aug 9 • 25

published a model 2 months ago

z369217411/Qwen3-30B-A3B-GRPO-W4A4-NoOverlong-Step800

Reinforcement Learning • 31B • Updated Aug 9 • 25

updated 3 models 2 months ago

z369217411/Qwen3-30B-A3B-GRPO-3Loss-Step800

Text Generation • 31B • Updated Jul 27 • 23

z369217411/Qwen3-30B-A3B-GRPO-BF16-Control-Step800

Text Generation • 31B • Updated Jul 27 • 32

z369217411/Qwen3-30B-A3B-GRPO-LowPrecision-Control-Step410

Text Generation • 31B • Updated Jul 27 • 21

published 3 models 2 months ago

z369217411/Qwen3-30B-A3B-GRPO-LowPrecision-Control-Step410

Text Generation • 31B • Updated Jul 27 • 21

z369217411/Qwen3-30B-A3B-GRPO-3Loss-Step800

Text Generation • 31B • Updated Jul 27 • 23

z369217411/Qwen3-30B-A3B-GRPO-BF16-Control-Step800

Text Generation • 31B • Updated Jul 27 • 32

updated a collection 3 months ago

Qwen3-30B-A3B W4A4-QAT vs BF16 Checkpoints

Collection

Seven step-matched Qwen3-30B-A3B DAPO pairs: FFN W4A4-QAT BF16 master weights (not packed W4A4) and a BF16 baseline. • 14 items • Updated Jul 12