common : refactor '-o' option (#12278)

As discussed in PR 'llama-tts : add -o option' (#12042):

* common_params : 'out_file' string is the only output file name parameter left in common_params. It's intended to be used in all example programs implementing an '-o' option.

* cvector-generator, export-lora, imatrix : default output filenames moved from 'common_params' to the 'main()' of each example program.

diff --git a/common/arg.cpp b/common/arg.cpp
index b96a5678f73469238e4939201a624dd9c7c94786..8531f0871d44a8c500f6a17ea726c37397a87016 100644 (file)
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -1867,16 +1867,9 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ).set_examples({LLAMA_EXAMPLE_PASSKEY}));
     add_opt(common_arg(
         {"-o", "--output", "--output-file"}, "FNAME",
-        string_format("output file (default: '%s')",
-            ex == LLAMA_EXAMPLE_EXPORT_LORA
-                ? params.lora_outfile.c_str()
-                : ex == LLAMA_EXAMPLE_CVECTOR_GENERATOR
-                    ? params.cvector_outfile.c_str()
-                    : params.out_file.c_str()),
+        string_format("output file (default: '%s')", params.out_file.c_str()),
         [](common_params & params, const std::string & value) {
             params.out_file = value;
-            params.cvector_outfile = value;
-            params.lora_outfile = value;
         }
     ).set_examples({LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_CVECTOR_GENERATOR, LLAMA_EXAMPLE_EXPORT_LORA}));
     add_opt(common_arg(

diff --git a/common/common.h b/common/common.h
index 733f7f1c8d662a7048235d7f9dd7a44356c961e3..1c0f19977497662dbb21a7f4329fda0a28534f4d 100644 (file)
--- a/common/common.h
+++ b/common/common.h
@@ -407,8 +407,6 @@ struct common_params {
     int32_t i_pos  = -1;  // position of the passkey in the junk text
 
     // imatrix params
-    std::string out_file = "imatrix.dat"; // save the resulting imatrix to this file
-
     int32_t n_out_freq  = 10; // output the imatrix every n_out_freq iterations
     int32_t n_save_freq =  0; // save the imatrix every n_save_freq iterations
     int32_t i_chunk     =  0; // start processing from this chunk
@@ -420,16 +418,16 @@ struct common_params {
     int n_pca_batch = 100;
     int n_pca_iterations = 1000;
     dimre_method cvector_dimre_method = DIMRE_METHOD_PCA;
-    std::string cvector_outfile       = "control_vector.gguf";
     std::string cvector_positive_file = "examples/cvector-generator/positive.txt";
     std::string cvector_negative_file = "examples/cvector-generator/negative.txt";
 
     bool spm_infill = false; // suffix/prefix/middle pattern for infill
 
-    std::string lora_outfile = "ggml-lora-merged-f16.gguf";
-
     // batched-bench params
     bool batched_bench_output_jsonl = false;
+
+    // common params
+    std::string out_file; // output filename for all example programs
 };
 
 // call once at the start of a program if it uses libcommon

diff --git a/examples/cvector-generator/cvector-generator.cpp b/examples/cvector-generator/cvector-generator.cpp
index 413b71d34c52ba1338ae2cb15e7929b5fd214312..c72528dac3ff009c50c2dedbf39140f3fe87b28c 100644 (file)
--- a/examples/cvector-generator/cvector-generator.cpp
+++ b/examples/cvector-generator/cvector-generator.cpp
@@ -394,6 +394,8 @@ static int prepare_entries(common_params & params, train_context & ctx_train) {
 int main(int argc, char ** argv) {
     common_params params;
 
+    params.out_file = "control_vector.gguf";
+
     if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_CVECTOR_GENERATOR, print_usage)) {
         return 1;
     }
@@ -498,7 +500,7 @@ int main(int argc, char ** argv) {
     }
 
     // write output vectors to gguf
-    export_gguf(ctx_train.v_final, params.cvector_outfile, model_hint);
+    export_gguf(ctx_train.v_final, params.out_file, model_hint);
 
     llama_backend_free();
 

diff --git a/examples/export-lora/export-lora.cpp b/examples/export-lora/export-lora.cpp
index 91238e4beb26c8f4fbc05076e336efb608ad75f6..e7d0fbfffedb042140bb41f2b3c365ec531ee8a3 100644 (file)
--- a/examples/export-lora/export-lora.cpp
+++ b/examples/export-lora/export-lora.cpp
@@ -413,20 +413,22 @@ static void print_usage(int, char ** argv) {
 int main(int argc, char ** argv) {
     common_params params;
 
+    params.out_file = "ggml-lora-merged-f16.gguf";
+
     if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_EXPORT_LORA, print_usage)) {
         return 1;
     }
 
     g_verbose = (params.verbosity > 1);
     try {
-        lora_merge_ctx ctx(params.model, params.lora_adapters, params.lora_outfile, params.cpuparams.n_threads);
+        lora_merge_ctx ctx(params.model, params.lora_adapters, params.out_file, params.cpuparams.n_threads);
         ctx.run_merge();
     } catch (const std::exception & err) {
         fprintf(stderr, "%s\n", err.what());
         exit(EXIT_FAILURE);
     }
 
-    printf("done, output file is %s\n", params.lora_outfile.c_str());
+    printf("done, output file is %s\n", params.out_file.c_str());
 
     return 0;
 }

diff --git a/examples/imatrix/imatrix.cpp b/examples/imatrix/imatrix.cpp
index 4edc0bfacf1259bddcd58396430de90be7d3206e..91649c45065f470755ba2833becd240dda7b41f5 100644 (file)
--- a/examples/imatrix/imatrix.cpp
+++ b/examples/imatrix/imatrix.cpp
@@ -206,9 +206,6 @@ bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void *
 
 void IMatrixCollector::save_imatrix(int ncall) const {
     auto fname = m_params.out_file;
-    if (fname.empty()) {
-        fname = "imatrix.dat";
-    }
 
     if (ncall > 0) {
         fname += ".at_";
@@ -583,6 +580,8 @@ static bool compute_imatrix(llama_context * ctx, const common_params & params) {
 int main(int argc, char ** argv) {
     common_params params;
 
+    params.out_file = "imatrix.dat" ;
+
     params.n_ctx = 512;
     params.logits_all = true;
     params.escape = false;