Which custom code this model wants to run? Could you please explain me? I was using Llama.cpp.
#12
by
JLouisBiz
- opened
INFO:hf-to-gguf:Set model tokenizer
The repository for moonshotai/Moonlight-16B-A3B-Instruct contains custom code which must be executed to correctly load the model. You can inspect the repository content at https://hf.co/moonshotai/Moonlight-16B-A3B-Instruct.
You can avoid this prompt in future by passing the argument trust_remote_code=True.
Do you wish to run the custom code? [y/N]
As far as I know, this type of model is not supported by Llama.cpp.
There was an attempt at converting it into the correct format for Llama.cpp to run (GGUF format), but there's a report claiming that the converted model is not really functional.
https://huggingface.co/mmnga/Moonlight-16B-A3B-Instruct-gguf/discussions/1