]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 4afcc37)
quantize : use `map` to assign quantization type from `string` (#1191)
authorPavol Rusnak <redacted>
Wed, 26 Apr 2023 16:43:27 +0000 (18:43 +0200)
committerGitHub <redacted>
Wed, 26 Apr 2023 16:43:27 +0000 (18:43 +0200)
commit859fee6dfb00fab7ce6bc215b4adae78d82f4759
tree6f324d31645fe980ab2a3e0745870dd0592bff36tree
parent4afcc378698e057fcde64e23eb664e5af8dd6956commit | diff
quantize : use `map` to assign quantization type from `string` (#1191)

instead of `int` (while `int` option still being supported)

This allows the following usage:

`./quantize ggml-model-f16.bin ggml-model-q4_0.bin q4_0`

instead of:

`./quantize ggml-model-f16.bin ggml-model-q4_0.bin 2`
.devops/tools.sh diff | blob | history
README.md diff | blob | history
examples/quantize/quantize.cpp diff | blob | history
Packaging of ggml-org/llama.cpp