diff --git a/examples/common.cpp b/examples/common.cpp index a4fea4a..e89df53 100644 --- a/examples/common.cpp +++ b/examples/common.cpp @@ -351,7 +351,7 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) { } if (params.prompt_cache_all && (params.interactive || params.interactive_first || - params.instruct || params.antiprompt.size())) { + params.instruct)) { fprintf(stderr, "error: --prompt-cache-all not supported in interactive mode yet\n"); gpt_print_usage(argc, argv, default_params); exit(1); @@ -373,8 +373,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { fprintf(stderr, " -ins, --instruct run in instruction mode (use with Alpaca models)\n"); fprintf(stderr, " --multiline-input allows you to write or paste multiple lines without ending each in '\\'\n"); fprintf(stderr, " -r PROMPT, --reverse-prompt PROMPT\n"); - fprintf(stderr, " run in interactive mode and poll user input upon seeing PROMPT (can be\n"); - fprintf(stderr, " specified more than once for multiple prompts).\n"); + fprintf(stderr, " halt generation at PROMPT, return control in interactive mode\n"); + fprintf(stderr, " (can be specified more than once for multiple prompts).\n"); fprintf(stderr, " --color colorise output to distinguish prompt and user input from generations\n"); fprintf(stderr, " -s SEED, --seed SEED RNG seed (default: -1, use random seed for < 0)\n"); fprintf(stderr, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads); diff --git a/examples/main/main.cpp b/examples/main/main.cpp index 18673ed..4d886f8 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -208,8 +208,8 @@ int main(int argc, char ** argv) { params.antiprompt.push_back("### Instruction:\n\n"); } - // enable interactive mode if reverse prompt or interactive start is specified - if (params.antiprompt.size() != 0 || params.interactive_first) { + // enable interactive mode if interactive start is specified + if (params.interactive_first) { params.interactive = true; } @@ -305,7 +305,7 @@ int main(int argc, char ** argv) { std::vector embd; - while (n_remain != 0 || params.interactive) { + while ((n_remain != 0 && !is_antiprompt) || params.interactive) { // predict if (embd.size() > 0) { // infinite text generation via context swapping @@ -503,9 +503,8 @@ int main(int argc, char ** argv) { console_set_color(con_st, CONSOLE_COLOR_DEFAULT); } - // in interactive mode, and not currently processing queued inputs; - // check if we should prompt the user for more - if (params.interactive && (int) embd_inp.size() <= n_consumed) { + // if not currently processing queued inputs; + if ((int) embd_inp.size() <= n_consumed) { // check for reverse prompt if (params.antiprompt.size()) { @@ -516,10 +515,21 @@ int main(int argc, char ** argv) { is_antiprompt = false; // Check if each of the reverse prompts appears at the end of the output. + // If we're not running interactively, the reverse prompt might be tokenized with some following characters + // so we'll compensate for that by widening the search window a bit. for (std::string & antiprompt : params.antiprompt) { - if (last_output.find(antiprompt.c_str(), last_output.length() - antiprompt.length(), antiprompt.length()) != std::string::npos) { - is_interacting = true; + size_t extra_padding = params.interactive ? 0 : 2; + size_t search_start_pos = last_output.length() > static_cast(antiprompt.length() + extra_padding) + ? last_output.length() - static_cast(antiprompt.length() + extra_padding) + : 0; + + if (last_output.find(antiprompt.c_str(), search_start_pos) != std::string::npos) { + if (params.interactive) { + is_interacting = true; + console_set_color(con_st, CONSOLE_COLOR_USER_INPUT); + } is_antiprompt = true; + fflush(stdout); break; } }