Mingming Yin

mmyin's activity

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

New activity in Qwen/Qwen3-8B 7 months ago

Why is max_position_embeddings set to 40K in config.json but original_max_position_embeddings is 32K in the README? Which one should be used?

➕ 2

1

#17 opened 7 months ago by

mmyin