Transformers
llama
text-generation-inference

GGUF version?

#2
by rambocoder - opened

@TheBloke are you able to create GGUF version of this model? And I heart that in your new GGUF models you are not using 7zip to split files but instead regular cat works to join the model's chunks into one.

Yes I'm going to start making GGUF repos for previously released models quite soon - hopefully starting tomorrow. Llama 2 models like this one will be prioritised.

And yeah, not sure why I used ZIP in the first place. split is so much quicker!

Sign up or log in to comment