dont build quantize
This commit is contained in:
parent
4f5faf9612
commit
1d48db4f63
2 changed files with 6 additions and 2 deletions
5
Makefile
5
Makefile
|
@ -139,7 +139,7 @@ $(info I CC: $(CCV))
|
|||
$(info I CXX: $(CXXV))
|
||||
$(info )
|
||||
|
||||
default: llamalib quantize llamalib_blas
|
||||
default: llamalib llamalib_blas
|
||||
|
||||
#
|
||||
# Build library
|
||||
|
@ -187,6 +187,9 @@ llamalib_blas: ggml_blas.o ggml_v1.o expose.o common.o llama_adapter.o gpttype_a
|
|||
quantize: examples/quantize/quantize.cpp ggml.o llama.o
|
||||
$(CXX) $(CXXFLAGS) examples/quantize/quantize.cpp ggml.o llama.o -o quantize $(LDFLAGS)
|
||||
|
||||
quantize_gptj: ggml.o llama.o
|
||||
$(CXX) $(CXXFLAGS) otherarch/gptj_quantize.cpp ggml.o llama.o -o quantize_gptj $(LDFLAGS)
|
||||
|
||||
perplexity: examples/perplexity/perplexity.cpp ggml.o llama.o common.o
|
||||
$(CXX) $(CXXFLAGS) examples/perplexity/perplexity.cpp ggml.o llama.o common.o -o perplexity $(LDFLAGS)
|
||||
|
||||
|
|
|
@ -1,6 +1,6 @@
|
|||
#include "ggml.h"
|
||||
|
||||
#include "utils.h"
|
||||
#include "otherarch/utils.h"
|
||||
|
||||
#include <cassert>
|
||||
#include <cmath>
|
||||
|
@ -283,6 +283,7 @@ bool gptj_model_quantize(const std::string & fname_inp, const std::string & fnam
|
|||
// ./gpt-2-quantize models/gpt-2-117M/ggml-model.bin models/gpt-2-117M/ggml-model-quant.bin type
|
||||
//
|
||||
int main(int argc, char ** argv) {
|
||||
ggml_time_init();
|
||||
if (argc != 4) {
|
||||
fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]);
|
||||
fprintf(stderr, " type = 2 - q4_0\n");
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue