vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README-sycl.md
#	README.md
#	flake.lock
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-06-17 15:14:47 +08:00
commit 967c1d8df5
91 changed files with 32045 additions and 27474 deletions
Download patch file Download diff file Expand all files Collapse all files

60
common/common.cpp
View file

@ -1577,6 +1577,7 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
return true;
}
params.out_file = argv[i];
params.cvector_outfile = argv[i];
return true;
}
if (arg == "-ofreq" || arg == "--output-frequency") {
@ -1611,6 +1612,55 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.i_chunk = std::stoi(argv[i]);
return true;
}
// cvector params
if (arg == "--completions-file") {
if (++i >= argc) {
invalid_param = true;
return true;
}
params.cvector_completions_file = argv[i];
return true;
}
if (arg == "--positive-file") {
if (++i >= argc) {
invalid_param = true;
return true;
}
params.cvector_positive_file = argv[i];
return true;
}
if (arg == "--negative-file") {
if (++i >= argc) {
invalid_param = true;
return true;
}
params.cvector_negative_file = argv[i];
return true;
}
if (arg == "--completions") {
if (++i >= argc) {
invalid_param = true;
return true;
}
params.n_completions = std::stoi(argv[i]);
return true;
}
if (arg == "--pca-batch") {
if (++i >= argc) {
invalid_param = true;
return true;
}
params.n_pca_batch = std::stoi(argv[i]);
return true;
}
if (arg == "--pca-iter") {
if (++i >= argc) {
invalid_param = true;
return true;
}
params.n_pca_iterations = std::stoi(argv[i]);
return true;
}
#ifndef LOG_DISABLE_LOGS
// Parse args for logging parameters
if (log_param_single_parse(argv[i])) {
@ -1932,6 +1982,16 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
options.push_back({ "logging", " --log-append", "Don't truncate the old log file." });
#endif // LOG_DISABLE_LOGS
options.push_back({ "cvector" });
options.push_back({ "cvector", "-o, --output FNAME", "output file (default: '%s')", params.cvector_outfile.c_str() });
options.push_back({ "cvector", " --positive-file FNAME", "positive prompts file, one prompt per line (default: '%s')", params.cvector_positive_file.c_str() });
options.push_back({ "cvector", " --negative-file FNAME", "negative prompts file, one prompt per line (default: '%s')", params.cvector_negative_file.c_str() });
options.push_back({ "cvector", " --completions-file FNAME",
"completions file (default: '%s')", params.cvector_completions_file.c_str() });
options.push_back({ "cvector", " --completions N", "number of lines of completions file to use (default: %d)", params.n_completions });
options.push_back({ "cvector", " --batch-pca N", "batch size used for PCA. Larger batch runs faster, but uses more memory (default: %d)", params.n_pca_batch });
options.push_back({ "cvector", " --iter-pca N", "number of iterations used for PCA (default: %d)", params.n_pca_iterations });
printf("usage: %s [options]\n", argv[0]);
for (const auto & o : options) {