CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

imatrix : use GGUF by default

Browse Source 
Still uses the old format when the output filename ends with .dat
but this can be overridden with --output-format
This commit is contained in:
Francis Couture-Harpin
2025-07-23 21:33:53 -04:00
parent a12363bbf0
commit 53f65c354e
4 changed files with 24 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
common/arg.cpp
View File

@@ -2627,6 +2627,15 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.n_out_freq = value;
}
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
add_opt(common_arg(
{"--output-format"}, "{gguf,dat}",
string_format("output format for imatrix file (default: gguf except when output filename ends with .dat)"),
[](common_params & params, const std::string & value) {
/**/ if (value == "gguf") { params.imat_out_type = COMMON_IMATRIX_FORMAT_GGUF; }
else if (value == "dat") { params.imat_out_type = COMMON_IMATRIX_FORMAT_DAT; }
else { throw std::invalid_argument("invalid output format"); }
}
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
add_opt(common_arg(
{"--save-frequency"}, "N",
string_format("save an imatrix copy every N iterations (default: %d)", params.n_save_freq),