Kawrakow 66d575c45c llama : add Q3_K_XS (#5060) ...

* Add Q3_K_XS - intermediate size between Q2_K and Q3_K_S

* Q3_K_XS: quanize first 1/8 of ffn_down layers with Q4_K

Together with an importance matrix, this brings perplexity
for LLaMA-v2-70B below the perplexity of the former Q2_K
with a 800 MB smaller quantized model size.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2024-01-22 12:43:33 +02:00

40 KiB

Raw Blame History

View Raw