kalomaze
/

Qwen3-16B-A3B

Model card Files Files and versions Community

Resources

View closed (0)

This model almost completely loses Chinese ablities

#14 opened 1 day ago by

Base version?

#13 opened 3 days ago by

Russian language is missing

#12 opened 6 days ago by

Please, share the custom vLLM source you made

#11 opened 7 days ago by

Update metadata 🤗

#10 opened 7 days ago by

Model seems to not be performing correctly

#9 opened 7 days ago by

Larger model?

#8 opened 7 days ago by

number of experts +

#7 opened 9 days ago by

Brainstorming

#6 opened 10 days ago by

Further training/distillation needed?

#5 opened 10 days ago by

Besides pruning..

#4 opened 10 days ago by

Context size? YaRN still supported?

#3 opened 10 days ago by

Variants

#2 opened 10 days ago by

code

#1 opened 10 days ago by