root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 03:44:35 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

examples/gguf : no need to keep q option for quantization any more

Browse Source
This commit is contained in:
M. Yusuf Sarıgöz 2023-08-17 08:56:42 +03:00
parent 5ec18934ad
commit 42f8fe1927
1 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
examples/gguf/gguf.cpp
View File

@ -233,16 +233,13 @@ int main(int argc, char ** argv) {
const std::string fname(argv[1]);
const std::string mode (argv[2]);
GGML_ASSERT((mode == "r" || mode == "w" || mode == "q") && "mode must be r, w or q");
GGML_ASSERT((mode == "r" || mode == "w") && "mode must be r or w");
if (mode == "w") {
GGML_ASSERT(gguf_ex_write(fname) && "failed to write gguf file");
} else if (mode == "r") {
GGML_ASSERT(gguf_ex_read_0(fname) && "failed to read gguf file");
GGML_ASSERT(gguf_ex_read_1(fname) && "failed to read gguf file");
} else if (mode == "q") {
llama_model_quantize_params params = llama_model_quantize_default_params();
llama_model_quantize(fname.c_str(), "quant.gguf", &params);
}
return 0;