Stephan Walter 3e6e70d8e8 Add enum llama_ftype, sync ggml_type to model files (#709)		%!s(int64=2) %!d(string=hai) anos
..
CMakeLists.txt	7f4c5c6651 llama : fix linkage with mingw (#551)	%!s(int64=2) %!d(string=hai) anos
README.md	a316a425d0 Overhaul the examples structure	%!s(int64=2) %!d(string=hai) anos
quantize.cpp	3e6e70d8e8 Add enum llama_ftype, sync ggml_type to model files (#709)	%!s(int64=2) %!d(string=hai) anos

quantize

réplica de https://github.com/cturan/llama.cpp

TODO