diff --git a/common/common.cpp b/common/common.cpp index 5fd33e2a1..b8323c1c1 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -1062,8 +1062,8 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa params.ignore_eos = true; return true; } - if (arg == "--no-penalize-nl") { - sparams.penalize_nl = false; + if (arg == "--penalize-nl") { + sparams.penalize_nl = true; return true; } if (arg == "-l" || arg == "--logit-bias") { @@ -1373,7 +1373,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { printf(" -dt N, --defrag-thold N\n"); printf(" KV cache defragmentation threshold (default: %.1f, < 0 - disabled)\n", params.defrag_thold); printf(" --ignore-eos ignore end of stream token and continue generating (implies --logit-bias 2-inf)\n"); - printf(" --no-penalize-nl do not penalize newline token\n"); + printf(" --penalize-nl penalize newline tokens\n"); printf(" --temp N temperature (default: %.1f)\n", (double)sparams.temp); printf(" --all-logits return logits for all tokens in the batch (default: disabled)\n"); printf(" --hellaswag compute HellaSwag score over random tasks from datafile supplied with -f\n"); @@ -2489,7 +2489,7 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l fprintf(stream, "n_predict: %d # default: -1 (unlimited)\n", params.n_predict); fprintf(stream, "n_probs: %d # only used by server binary, default: 0\n", sparams.n_probs); fprintf(stream, "no_mmap: %s # default: false\n", !params.use_mmap ? "true" : "false"); - fprintf(stream, "no_penalize_nl: %s # default: false\n", !sparams.penalize_nl ? "true" : "false"); + fprintf(stream, "penalize_nl: %s # default: false\n", sparams.penalize_nl ? "true" : "false"); fprintf(stream, "ppl_output_type: %d # default: 0\n", params.ppl_output_type); fprintf(stream, "ppl_stride: %d # default: 0\n", params.ppl_stride); fprintf(stream, "presence_penalty: %f # default: 0.0\n", sparams.penalty_present);