Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
Paper
•
2501.11873
•
Published
•
66
Tu Jianhong
tuhahaha
·
AI & ML interests
None yet
Recent Activity
new activity
12 days ago
Qwen/Qwen3-235B-A22B:Qwen3 not Using Tools in Complex Prompts Unlike QwQ-32B
new activity
3 months ago
Qwen/Qwen2.5-14B-Instruct-1M:About function calling failures using the huggingface transformer
Organizations
