Hugging Face's logo

Qwen
/
Qwen3-Next-80B-A3B-Instruct

Text Generation
Transformers
Safetensors
qwen3_next
conversational
Model card Files
xet
Community
32

Is it possible to finetune with ms-swift?

#12
by phosira - opened
Discussion
phosira

I want to finetune this model with ms-swift megatron-lm.

exploding-gradients

Coming soon ...

study-hjt

https://github.com/modelscope/ms-swift/pull/5764

https://github.com/modelscope/ms-swift/tree/main/examples/models/qwen3_next

supported

ζˆͺ屏2025-09-14 11 44 31
minethrower

Is it possible to fine-tune MTP (multi-token prediction) head as well?

Sign up or log in to comment