Can only be used for continuous pre-training, and please follow the original context template.

An experimental qwen3 architecture alignment model that attempts to merge yi Coder 1.5B and qwen3 1.7B into the Qwen3 architecture.

Downloads last month
6
Safetensors
Model size
3B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for win10/Fused-Yi-Qwen3-3B

Merge model
this model