diff options
| author | Yann Follet <131855179+YannFollet@users.noreply.github.com> | 2024-01-14 00:09:08 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-13 18:09:08 +0200 |
| commit | 722d33f34ec74c6f7046109f936d0928ffe171bc (patch) | |
| tree | 15cf24a08c4973aa2a07f9842699caff800f1957 /common | |
| parent | c30b1ef39aeba497a943416d2897d69fee055b96 (diff) | |
main : add parameter --no-display-prompt (#4541)
* add the parameter : --no-display-prompt , combine with --log-disable it will display only the generated tokens
* remove empty line
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'common')
| -rw-r--r-- | common/common.cpp | 6 | ||||
| -rw-r--r-- | common/common.h | 1 |
2 files changed, 6 insertions, 1 deletions
diff --git a/common/common.cpp b/common/common.cpp index 322b9f91..c11006bc 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -617,6 +617,8 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) { params.numa = true; } else if (arg == "--verbose-prompt") { params.verbose_prompt = true; + } else if (arg == "--no-display-prompt") { + params.display_prompt = false; } else if (arg == "-r" || arg == "--reverse-prompt") { if (++i >= argc) { invalid_param = true; @@ -936,11 +938,12 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { printf(" -mg i, --main-gpu i the GPU to use for the model (with split-mode = none),\n"); printf(" or for intermediate results and KV (with split-mode = row) (default: %d)\n", params.main_gpu); #endif + printf(" --verbose-prompt print a verbose prompt before generation (default: %s)\n", params.verbose_prompt ? "true" : "false"); + printf(" --no-display-prompt don't print prompt at generation (default: %s)\n", !params.display_prompt ? "true" : "false"); printf(" -gan N, --grp-attn-n N\n"); printf(" group-attention factor (default: %d)\n", params.grp_attn_n); printf(" -gaw N, --grp-attn-w N\n"); printf(" group-attention width (default: %.1f)\n", (double)params.grp_attn_w); - printf(" --verbose-prompt print prompt before generation\n"); printf(" -dkvc, --dump-kv-cache\n"); printf(" verbose print of the KV cache\n"); printf(" -nkvo, --no-kv-offload\n"); @@ -1582,6 +1585,7 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l fprintf(stream, "min_p: %f # default: 0.0\n", sparams.min_p); fprintf(stream, "typical_p: %f # default: 1.0\n", sparams.typical_p); fprintf(stream, "verbose_prompt: %s # default: false\n", params.verbose_prompt ? "true" : "false"); + fprintf(stream, "display_prompt: %s # default: true\n", params.display_prompt ? "true" : "false"); } // diff --git a/common/common.h b/common/common.h index f29be5b5..09646824 100644 --- a/common/common.h +++ b/common/common.h @@ -126,6 +126,7 @@ struct gpt_params { bool use_mlock = false; // use mlock to keep model in memory bool numa = false; // attempt optimizations that help on some NUMA systems bool verbose_prompt = false; // print prompt tokens before generation + bool display_prompt = true; // print prompt before generation bool infill = false; // use infill mode bool dump_kv_cache = false; // dump the KV cache contents for debugging purposes bool no_kv_offload = false; // disable KV offloading |