wang

wzx111's activity

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

New activity in wzx111/Qwen3-1.7B-MATH-GDPO 4 months ago

Which post-training method was actually used for this model, GDPO or GRPO?

1

#1 opened 4 months ago by

roseblooming

New activity in Qwen/Qwen3-235B-A22B 11 months ago

是不是奖励函数没有ngram重复度惩罚

2

#7 opened 12 months ago by

wzx111

New activity in Qwen/Qwen3-1.7B 12 months ago

【Evaluation】Best practice for evaluating Qwen3 !!

🚀🔥 2

1

#2 opened 12 months ago by

wangxingjun778

New activity in wzx111/Qwen2.5-1.5B-Open-R1-GRPO 12 months ago

Improve language tag

#1 opened 12 months ago by

lbourdois