I wonder how to merge my PEFT adapter with the base model and finally get a new whole model?

[P1sc3s007]

I tried many time and found a point:
When I search their lora_weight to be merged, it looks like

But I don’t have that “bin” model, I just got a .safetensors file. Maybe it’s the key of these warnings?
After I train, it straightly output a .safetensors file and I don’t know how to merge it to the base model……