Alternative quantizations.

#1
by ZeroWw - opened

These are my own quantizations (updated almost daily).

The difference with normal quantizations is that I quantize the output and embed tensors to f16.
and the other tensors to 15_k,q6_k or q8_0.
This creates models that are little or not degraded at all and have a smaller size.
They run at about 3-6 t/sec on CPU only using llama.cpp
And obviously faster on computers with potent GPUs

Looks cool

appvoid changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment