vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : add Q4_3 quantization (#1082)

Browse source
This commit is contained in:
Georgi Gerganov 2023-04-20 20:35:53 +03:00 • committed by GitHub
parent 6a9661ea5a
commit e0305ead3a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 293 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View file

@ -15,6 +15,7 @@ int main(int argc, char ** argv) {
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);
return 1;
}