Nicholas Davidson

icon company SWE AI/ML @ Cisco | ML Research Assistant @ UCLA Health icon location Los Angeles, CA

Results 2 comments of Nicholas Davidson

Will there be support for models with custom architecture (not only mistral or gpt based)?

@ycros Mistral-v0.2 uses a Rope Theta value of 1e6 and removed sliding window attention should be easy to fix within the model config parameters. @vgel I'm interested in getting this...

Issue with convert-lora-to-ggml.py

@Gunnar-Stunnar I am running into a similar error with the conversion script when trying to convert a lora from the StableLM arch derived model. I'll update if I can find...