]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: e85bb1a)
train : move number of gpu layers argument parsing to common/train.cpp (#4074)
authorJiří Podivín <redacted>
Fri, 17 Nov 2023 15:19:16 +0000 (16:19 +0100)
committerGitHub <redacted>
Fri, 17 Nov 2023 15:19:16 +0000 (17:19 +0200)
commitba4cf5c0bf37a729d29e899dadf14541cddd23d4
tree9dcf5b40fc32a57c0c7b602a8e47cf8c4b7583a6tree
parente85bb1a8e736228a1f0d965777de5f77f22834b8commit | diff
train : move number of gpu layers argument parsing to common/train.cpp (#4074)

- introduces help entry for the argument
 - cuts '--gpu-layers' form in order to simplify usage and documentation.

Signed-off-by: Jiri Podivin <redacted>
Co-authored-by: Jiri Podivin <redacted>
common/train.cpp diff | blob | history
examples/finetune/finetune.cpp diff | blob | history
Packaging of ggml-org/llama.cpp