mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-04-25 21:16:05 +00:00

History

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`

2023-04-26 18:43:27 +02:00

CMakeLists.txt

llama : fix linkage with mingw (#551 )

2023-03-28 21:23:09 +03:00

quantize.cpp

quantize : use map to assign quantization type from string (#1191 )

2023-04-26 18:43:27 +02:00

README.md

Overhaul the examples structure

2023-03-25 20:26:40 +02:00

README.md

quantize

TODO