From 62cfc54f77e519057110265b52b0d614fa363e2a Mon Sep 17 00:00:00 2001 From: unbounded Date: Sat, 8 Apr 2023 00:09:18 +0200 Subject: Add quantize-stats command for testing quantization (#728) Command that calculates some statistics over the errors introduced by quantization, like mean square error, max error and some percentile errors for layer weights. Should be useful for testing quantization improvements. Exposes some internal state from ggml and llama for testing --- Makefile | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'Makefile') diff --git a/Makefile b/Makefile index 96c19de..c55338e 100644 --- a/Makefile +++ b/Makefile @@ -149,7 +149,7 @@ common.o: examples/common.cpp examples/common.h $(CXX) $(CXXFLAGS) -c examples/common.cpp -o common.o clean: - rm -vf *.o main quantize perplexity embedding + rm -vf *.o main quantize quantize-stats perplexity embedding main: examples/main/main.cpp ggml.o llama.o common.o $(CXX) $(CXXFLAGS) examples/main/main.cpp ggml.o llama.o common.o -o main $(LDFLAGS) @@ -160,6 +160,9 @@ main: examples/main/main.cpp ggml.o llama.o common.o quantize: examples/quantize/quantize.cpp ggml.o llama.o $(CXX) $(CXXFLAGS) examples/quantize/quantize.cpp ggml.o llama.o -o quantize $(LDFLAGS) +quantize-stats: examples/quantize-stats/quantize-stats.cpp ggml.o llama.o + $(CXX) $(CXXFLAGS) examples/quantize-stats/quantize-stats.cpp ggml.o llama.o -o quantize-stats $(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) -- cgit v1.2.3