diff options
author | Pavol Rusnak <pavol@rusnak.io> | 2023-04-26 18:43:27 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-04-26 18:43:27 +0200 |
commit | 859fee6dfb00fab7ce6bc215b4adae78d82f4759 (patch) | |
tree | 6f324d31645fe980ab2a3e0745870dd0592bff36 /examples/quantize/quantize.cpp | |
parent | 4afcc378698e057fcde64e23eb664e5af8dd6956 (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`
Diffstat (limited to 'examples/quantize/quantize.cpp')
-rw-r--r-- | examples/quantize/quantize.cpp | 30 |
1 files changed, 24 insertions, 6 deletions
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index ad39a80..ec7f91a 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -2,8 +2,17 @@ #include "llama.h" #include <cstdio> +#include <map> #include <string> +static const std::map<std::string, enum llama_ftype> LLAMA_FTYPE_MAP = { + {"q4_0", LLAMA_FTYPE_MOSTLY_Q4_0}, + {"q4_1", LLAMA_FTYPE_MOSTLY_Q4_1}, + {"q4_2", LLAMA_FTYPE_MOSTLY_Q4_2}, + {"q4_3", LLAMA_FTYPE_MOSTLY_Q4_3}, + {"q8_0", LLAMA_FTYPE_MOSTLY_Q8_0}, +}; + // usage: // ./quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type // @@ -12,11 +21,9 @@ int main(int argc, char ** argv) { if (argc < 4) { fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type [nthread]\n", argv[0]); - fprintf(stderr, " type = %d - q4_0\n", LLAMA_FTYPE_MOSTLY_Q4_0); - fprintf(stderr, " type = %d - q4_1\n", LLAMA_FTYPE_MOSTLY_Q4_1); - fprintf(stderr, " type = %d - q4_2\n", LLAMA_FTYPE_MOSTLY_Q4_2); - fprintf(stderr, " type = %d - q4_3\n", LLAMA_FTYPE_MOSTLY_Q4_3); - fprintf(stderr, " type = %d - q8_0\n", LLAMA_FTYPE_MOSTLY_Q8_0); + for (auto it = LLAMA_FTYPE_MAP.begin(); it != LLAMA_FTYPE_MAP.end(); it++) { + fprintf(stderr, " type = \"%s\" or %d\n", it->first.c_str(), it->second); + } return 1; } @@ -30,7 +37,18 @@ int main(int argc, char ** argv) { const std::string fname_inp = argv[1]; const std::string fname_out = argv[2]; - const enum llama_ftype ftype = (enum llama_ftype)atoi(argv[3]); + enum llama_ftype ftype; + if (argv[3][0] == 'q') { + auto it = LLAMA_FTYPE_MAP.find(argv[3]); + if (it == LLAMA_FTYPE_MAP.end()) { + fprintf(stderr, "%s: unknown ftype '%s'\n", __func__, argv[3]); + return 1; + } + ftype = it->second; + } else { + ftype = (enum llama_ftype)atoi(argv[3]); + } + int nthread = argc > 4 ? atoi(argv[4]) : 0; const int64_t t_main_start_us = ggml_time_us(); |