diff options
Diffstat (limited to 'common')
| -rw-r--r-- | common/common.cpp | 60 | ||||
| -rw-r--r-- | common/common.h | 9 |
2 files changed, 69 insertions, 0 deletions
diff --git a/common/common.cpp b/common/common.cpp index 1591790e..73ff0e85 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -1576,6 +1576,7 @@ 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") { @@ -1610,6 +1611,55 @@ 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])) { @@ -1931,6 +1981,16 @@ 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) { diff --git a/common/common.h b/common/common.h index 2345d855..58ed72f4 100644 --- a/common/common.h +++ b/common/common.h @@ -232,6 +232,15 @@ struct gpt_params { bool process_output = false; // collect data for the output tensor bool compute_ppl = true; // whether to compute perplexity + + // cvector-generator params + int n_completions = 64; + int n_pca_batch = 20; + int n_pca_iterations = 1000; + std::string cvector_outfile = "control_vector.gguf"; + std::string cvector_completions_file = "examples/cvector-generator/completions.txt"; + std::string cvector_positive_file = "examples/cvector-generator/positive.txt"; + std::string cvector_negative_file = "examples/cvector-generator/negative.txt"; }; void gpt_params_handle_model_default(gpt_params & params); |