]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 771551a)
Better perplexity for 2- and 3-bit quantization for LLaMA-v2-70B (#2807)
authorKawrakow <redacted>
Sat, 26 Aug 2023 14:27:49 +0000 (17:27 +0300)
committerGitHub <redacted>
Sat, 26 Aug 2023 14:27:49 +0000 (17:27 +0300)
commit7592375403a0bd0456d5ec2cdf8350e591f04fb0
tree4a69f9bc75e6878b972844afbc497ffb5f3fecf6tree
parent771551a793c9976ed9cdfe7b8c69536af32af9f9commit | diff
Better perplexity for 2- and 3-bit quantization for LLaMA-v2-70B (#2807)

* Better perplexity for 2- and 3-bit quantization for the 70B model

* PR comment

---------

Co-authored-by: Iwan Kawrakow <redacted>
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp