sft_merged

Early DAPO-Math action-router SFT merged Qwen3-4B.

Merged full-weight Qwen3-4B router checkpoint from the PAgent project.

Downloads last month
4
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ivaning0919/pagent-router-sft-merged

Finetuned
Qwen/Qwen3-4B
Finetuned
(1075)
this model