From 25d4599e19de771c1bd2badbb2e0f1bdb1d70fe5 Mon Sep 17 00:00:00 2001 From: zhenweijin Date: Fri, 20 Sep 2024 19:06:39 +0800 Subject: [PATCH] remove unused files --- tests/CMakeLists.txt | 19 ---- tests/test-tokenizer-parallel.cpp | 180 ------------------------------ 2 files changed, 199 deletions(-) delete mode 100644 tests/test-tokenizer-parallel.cpp diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt index 8f991477c..08ad66b49 100644 --- a/tests/CMakeLists.txt +++ b/tests/CMakeLists.txt @@ -84,25 +84,6 @@ llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2 ARGS ${CMAKE llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf) llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf) -# build test-tokenizer-parallel target once and add many tests -add_executable(test-tokenizer-parallel test-tokenizer-parallel.cpp) -target_link_libraries(test-tokenizer-parallel PRIVATE common) -install(TARGETS test-tokenizer-parallel RUNTIME) - -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-bert-bge ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-bert-bge.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-command-r ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-command-r.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-deepseek-coder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-deepseek-coder.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-deepseek-llm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-deepseek-llm.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-falcon ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-gpt-2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-2.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-llama-bpe ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-llama-spm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-spm.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-mpt ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-mpt.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-phi-3 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-phi-3.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-qwen2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-qwen2.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf) -llama_test(test-tokenizer-parallel NAME test-tokenizer-parallel-starcoder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf) - # build test-tokenizer-1-bpe target once and add many tests add_executable(test-tokenizer-1-bpe test-tokenizer-1-bpe.cpp) target_link_libraries(test-tokenizer-1-bpe PRIVATE common) diff --git a/tests/test-tokenizer-parallel.cpp b/tests/test-tokenizer-parallel.cpp deleted file mode 100644 index cead81079..000000000 --- a/tests/test-tokenizer-parallel.cpp +++ /dev/null @@ -1,180 +0,0 @@ -#include "llama.h" -#include "common.h" -#include "console.h" - -#include -#include -#include -#include -#include -#include - -using llama_tests = std::map>; - -static llama_tests read_tests(const std::string & fname_inp, const std::string & fname_out) { - llama_tests tests; - - std::ifstream ifs_inp(fname_inp); - if (!ifs_inp) { - fprintf(stderr, "%s : error: could not open file '%s'\n", __func__, fname_inp.c_str()); - return tests; - } - - std::string sraw((std::istreambuf_iterator(ifs_inp)), std::istreambuf_iterator()); - - std::ifstream ifs_out(fname_out); - if (!ifs_out) { - fprintf(stderr, "%s : error: could not open file '%s'\n", __func__, fname_out.c_str()); - return tests; - } - - std::vector sout; - for (std::string line; std::getline(ifs_out, line);) { - sout.push_back(line); - } - - const std::string sep = "\n__ggml_vocab_test__\n"; - - std::vector sinp; - - size_t pos = 0; - while (pos < sraw.size()) { - const size_t next = sraw.find(sep, pos); - if (next == std::string::npos) { - sinp.push_back(sraw.substr(pos)); - break; - } - sinp.push_back(sraw.substr(pos, next - pos)); - pos = next + sep.size(); - } - - if (sinp.size() != sout.size()) { - fprintf(stderr, "%s : error: input and output files have different number of tests\n", __func__); - return tests; - } - - for (size_t i = 0; i < sinp.size(); ++i) { - const std::string & s = sinp[i]; - const std::string & o = string_strip(sout[i]); - - std::vector toks; - - size_t pos = 0; - while (pos < o.size()) { - size_t next = o.find(' ', pos); - if (next == std::string::npos) { - next = o.size(); - } - const std::string stok = o.substr(pos, next - pos); - toks.push_back(std::stoi(stok)); - pos = next + 1; - } - - tests[s] = toks; - } - - return tests; -} - -int main(int argc, char const *argv[]) { - - if (argc < 2) { - fprintf(stderr, "Usage: %s vocab-file \n", argv[0]); - return 1; - } - - const std::string fname = argv[1]; - - const std::string fname_inp = fname + ".inp"; - const std::string fname_out = fname + ".out"; - - fprintf(stderr, "%s : reading vocab from: '%s'\n", __func__, fname.c_str()); - - llama_model * model; - llama_context * ctx; - - llama_backend_init(); - - // load the vocab - { - auto mparams = llama_model_default_params(); - - mparams.vocab_only = true; - - model = llama_load_model_from_file(fname.c_str(), mparams); - - if (model == NULL) { - fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str()); - return 1; - } - - auto cparams = llama_context_default_params(); - - ctx = llama_new_context_with_model(model, cparams); - - if (ctx == NULL) { - fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str()); - llama_free_model(model); - return 1; - } - } - -#ifdef _WIN32 - // We need this for unicode console support - console::init(false, false); - atexit([]() { console::cleanup(); }); -#endif - - const int nthread = std::thread::hardware_concurrency(); - std::vector threads(nthread); - - bool success = true; - - const auto k_tests = [&]() -> llama_tests { - const auto res = read_tests(fname_inp, fname_out); - - if (res.empty()) { - fprintf(stderr, "%s : error: no tests found\n", __func__); - exit(1); - } - - return res; - }(); - - const bool add_special = false; - - for (int i = 0; i < nthread; i++) { - threads[i] = std::thread([&]() { - for (const auto & test_kv : k_tests) { - const std::vector res = llama_tokenize(ctx, test_kv.first, add_special, false); - - bool correct = res.size() == test_kv.second.size(); - for (int i = 0; i < (int) res.size() && correct; ++i) { - if (test_kv.second[i] != res[i]) { - correct = false; - } - } - - if (!correct) { - success = false; - } - } - }); - } - - for (int i = 0; i < nthread; i++) { - threads[i].join(); - } - - llama_free_model(model); - llama_free(ctx); - - llama_backend_free(); - - printf("\n"); - printf("Tests %s\n", success ? "passed" : "failed"); - - return success ? 0 : 3; -} - -