From 5ca93f7907f63f5b91520768a1bccb998f2e3817 Mon Sep 17 00:00:00 2001 From: brian khuu Date: Sat, 25 May 2024 22:58:56 +1000 Subject: [PATCH] main: replace --no-special with --special This also flips the default behavior of the output to not include control token by default. --- common/common.cpp | 6 +++--- common/common.h | 2 +- examples/main/main.cpp | 10 ++-------- 3 files changed, 6 insertions(+), 12 deletions(-) diff --git a/common/common.cpp b/common/common.cpp index 781f2166bb66a..65103c3c294d3 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -904,8 +904,8 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa params.interactive_specials = true; return true; } - if (arg == "--no-special") { - params.no_special = true; + if (arg == "--special") { + params.special = true; return true; } if (arg == "--embedding") { @@ -1366,9 +1366,9 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param printf(" -h, --help show this help message and exit\n"); printf(" --version show version and build info\n"); printf(" -i, --interactive run in interactive mode\n"); + printf(" --special special tokens output enabled\n"); printf(" --interactive-specials allow special tokens in user text, in interactive mode\n"); printf(" --interactive-first run in interactive mode and wait for input right away\n"); - printf(" --no-special control tokens output disabled\n"); printf(" -cnv, --conversation run in conversation mode (does not print special tokens and suffix/prefix)\n"); printf(" -ins, --instruct run in instruction mode (use with Alpaca models)\n"); printf(" -cml, --chatml run in chatml mode (use with ChatML-compatible models)\n"); diff --git a/common/common.h b/common/common.h index 5388f6b68973c..264504830a7f0 100644 --- a/common/common.h +++ b/common/common.h @@ -146,7 +146,7 @@ struct gpt_params { bool use_color = false; // use color to distinguish generations and inputs bool interactive = false; // interactive mode bool interactive_specials = false; // whether to allow special tokens from user, during interactive mode - bool no_special = false; // disable control token output + bool special = false; // enable special token output bool conversation = false; // conversation mode (does not print special tokens and suffix/prefix) bool chatml = false; // chatml mode (used for models trained on chatml syntax) bool prompt_cache_all = false; // save user input and generations to prompt cache diff --git a/examples/main/main.cpp b/examples/main/main.cpp index ac35772f1e133..44949ba869e70 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -740,16 +740,10 @@ int main(int argc, char ** argv) { // display text if (input_echo && display) { for (auto id : embd) { - const std::string token_str = llama_token_to_piece(ctx, id); + const std::string token_str = llama_token_to_piece(ctx, id, params.special); // Console/Stream Output - if (!llama_token_is_control(llama_get_model(ctx), id)) { - // Stream Output Token To Standard Output - fprintf(stdout, "%s", token_str.c_str()); - } else if (!params.no_special && !params.conversation) { - // Stream Control Token To Standard Output Stream - fprintf(stdout, "%s", token_str.c_str()); - } + fprintf(stdout, "%s", token_str.c_str()); // Record Displayed Tokens To Log // Note: Generated tokens are created one by one hence this check