quantized versions

#1
by Tdot123 - opened

Hi, will you also add the quantized versions?
Currently, the links are 404.

Also will the gguf versions use the fixed bpe tokenizer? I read that there were some problems with llama3 and gguf.

Thank you so much for your work, it is much appreciated!

VAGO solutions org

thank you @redponike
we will link to your quants!

DavidGF changed discussion status to closed

Sign up or log in to comment