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
16 days ago
Qwen/Qwen3-235B-A22B:Qwen3 not Using Tools in Complex Prompts Unlike QwQ-32B
new activity
4 months ago
Qwen/Qwen2.5-14B-Instruct-1M:About function calling failures using the huggingface transformer
Organizations
tuhahaha's activity
Qwen3 not Using Tools in Complex Prompts Unlike QwQ-32B
8
#20 opened 16 days ago
by
Anaudia
About function calling failures using the huggingface transformer
4
#4 opened 4 months ago
by
NYAGU
upvoted
a
paper
4 months ago
upvoted
a
paper
5 months ago
authored
a
paper
over 1 year ago
liked
a
model
almost 2 years ago