Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 13:28:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
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`
This commit is contained in:
Pavol Rusnak 2023-04-26 18:43:27 +02:00 committed by GitHub
parent 4afcc37869
commit 859fee6dfb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 27 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.devops/tools.sh
View File

@ -23,7 +23,7 @@ elif [[ $arg1 == '--all-in-one' || $arg1 == '-a' ]]; then
echo "Skip model quantization, it already exists: ${i/f16/q4_0}"
else
echo "Converting PTH to GGML: $i into ${i/f16/q4_0}..."
./quantize "$i" "${i/f16/q4_0}" 2
./quantize "$i" "${i/f16/q4_0}" q4_0
fi
done
else

4
README.md
View File

@ -203,8 +203,8 @@ python3 -m pip install -r requirements.txt
# convert the 7B model to ggml FP16 format
python3 convert.py models/7B/
# quantize the model to 4-bits (using method 2 = q4_0)
./quantize ./models/7B/ggml-model-f16.bin ./models/7B/ggml-model-q4_0.bin 2
# quantize the model to 4-bits (using q4_0 method)
./quantize ./models/7B/ggml-model-f16.bin ./models/7B/ggml-model-q4_0.bin q4_0
# run the inference
./main -m ./models/7B/ggml-model-q4_0.bin -n 128

30
examples/quantize/quantize.cpp
View File

@ -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();