How was this quantized?

#1
by jlinux - opened

Can you share how this was quantized? I am unable to quantize using convert.py from llama.cpp and successfully load it with BPE or SPM vocab. Your insights are appreciated :).

Closing.. llama.cpp has a pending merge request to support which successfully generates GGUF.

jlinux changed discussion status to closed

Sign up or log in to comment