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

quantize: be able to specify the token embedding tensor type

Browse source
This commit is contained in:
Iwan Kawrakow 2024-03-22 16:27:34 +02:00
parent 7883796f71
commit 0e826d12a5
3 changed files with 28 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/quantize/quantize.cpp
View file

@ -221,6 +221,12 @@ int main(int argc, char ** argv) {
} else {
usage(argv[0]);
}
} else if (strcmp(argv[arg_idx], "--token-embedding-type") == 0) {
if (arg_idx < argc-1) {
params.token_embedding_type = parse_ggml_type(argv[++arg_idx]);
} else {
usage(argv[0]);
}
} else if (strcmp(argv[arg_idx], "--allow-requantize") == 0) {
params.allow_requantize = true;
} else if (strcmp(argv[arg_idx], "--pure") == 0) {