From b5fe67f8c69113bd9354bc1adcfe2df6be323740 Mon Sep 17 00:00:00 2001 From: klosax <131523366+klosax@users.noreply.github.com> Date: Sat, 22 Jul 2023 14:21:24 +0200 Subject: Perplexity: Compute scores correlated to HellaSwag (#2312) * Add parameter --perplexity-lines to perplexity.cpp --- examples/common.cpp | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'examples/common.cpp') diff --git a/examples/common.cpp b/examples/common.cpp index 09901959..730b28bd 100644 --- a/examples/common.cpp +++ b/examples/common.cpp @@ -387,6 +387,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) { params.antiprompt.push_back(argv[i]); } else if (arg == "--perplexity") { params.perplexity = true; + } else if (arg == "--perplexity-lines") { + params.perplexity_lines = true; } else if (arg == "--ignore-eos") { params.logit_bias[llama_token_eos()] = -INFINITY; } else if (arg == "--no-penalize-nl") { @@ -512,7 +514,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { fprintf(stderr, " not recommended: doubles context memory required and no measurable increase in quality\n"); fprintf(stderr, " --temp N temperature (default: %.1f)\n", (double)params.temp); fprintf(stderr, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch); - fprintf(stderr, " --perplexity compute perplexity over the prompt\n"); + fprintf(stderr, " --perplexity compute perplexity over each ctx window of the prompt\n"); + fprintf(stderr, " --perplexity-lines compute perplexity over each line of the prompt\n"); fprintf(stderr, " --keep number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep); fprintf(stderr, " --chunks N max number of chunks to process (default: %d, -1 = all)\n", params.n_chunks); if (llama_mlock_supported()) { -- cgit v1.2.3