convert.py fails importing a new model architecture about llama.cpp HOT 3 CLOSED

If I add lm_head.linear1 and lm_head.linear2

Even if this works it will likely think this is just two linear .weight type projections in series, whereas to use a .bias it needs to do an affine projection.

I don't know enough about llama.cpp to help more, but IIRC the Qwen models have some affine projections in then and use .bias as well as .weight, so this might be worth a look.

from llama.cpp.

Can you provide some tips on what I need to modify to make this work?

If it's a variation of an existing architecture, you might be able to simply specify new optional tensors on model load and then detect their presence in the compute graph to use them when they are present.

This is kind of how StableLM2 1.6B support was added in #5052.

Also if there is any documentation on porting new model architectures I would appreciate it if you could point me to it.

https://github.com/ggerganov/llama.cpp/blob/master/docs/HOWTO-add-model.md

from llama.cpp.

from llama.cpp.