Yiming Tang

tangyiming's activity

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

New activity in Qwen/Qwen3-Next-80B-A3B-Instruct 2 months ago

Megatron Swift dpo training on Qwen/Qwen3-Next-80B-A3B-Instruct always always return nan loss. Why?

#45 opened 2 months ago by

tangyiming