From d01bccde9f759b24449fdaa16306b406a50eb367 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Tue, 18 Jul 2023 14:24:43 +0300 Subject: ci : integrate with ggml-org/ci (#2250) * ci : run ctest ggml-ci * ci : add open llama 3B-v2 tests ggml-ci * ci : disable wget progress output ggml-ci * ci : add open llama 3B-v2 tg tests for q4 and q5 quantizations ggml-ci * tests : try to fix tail free sampling test ggml-ci * ci : add K-quants ggml-ci * ci : add short perplexity tests ggml-ci * ci : add README.md * ppl : add --chunks argument to limit max number of chunks ggml-ci * ci : update README --- examples/common.cpp | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'examples/common.cpp') diff --git a/examples/common.cpp b/examples/common.cpp index 8705127c..fd6dbc0e 100644 --- a/examples/common.cpp +++ b/examples/common.cpp @@ -279,6 +279,12 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) { break; } params.n_keep = std::stoi(argv[i]); + } else if (arg == "--chunks") { + if (++i >= argc) { + invalid_param = true; + break; + } + params.n_chunks = std::stoi(argv[i]); } else if (arg == "-m" || arg == "--model") { if (++i >= argc) { invalid_param = true; @@ -515,6 +521,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { 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, " --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()) { fprintf(stderr, " --mlock force system to keep model in RAM rather than swapping or compressing\n"); } -- cgit v1.2.3