]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
Slight quantization improvement for Q4_K and Q5_K (llama/5361)
authorKawrakow <redacted>
Tue, 6 Feb 2024 15:28:02 +0000 (17:28 +0200)
committerGeorgi Gerganov <redacted>
Sat, 10 Feb 2024 07:30:58 +0000 (09:30 +0200)
commit82389b52e3a676ae0a6e7801a5fc048d76010607
treecb68e706c9e08aea35acb3cae1647ab8c7047de7
parent8f5bb5dce581976fc2e4c9d456ecdaebf5e2554d
Slight quantization improvement for Q4_K and Q5_K (llama/5361)

* Q4_K: slightly better quantization

* Q5_K: slightly better quantization

---------

Co-authored-by: Iwan Kawrakow <redacted>
src/ggml-quants.c