diff --git a/tests/test-tokenizer-1-bpe.cpp b/tests/test-tokenizer-1-bpe.cpp index 9c748a9fb..1f3c6c750 100644 --- a/tests/test-tokenizer-1-bpe.cpp +++ b/tests/test-tokenizer-1-bpe.cpp @@ -110,16 +110,16 @@ int main(int argc, char **argv) { for (int i = 0; i < nthread; ++i) { threads[i] = std::thread([i, nthread, ctx]() { - for (uint32_t cp = i; cp < 0x0010ffff; cp += nthread) { - if (!( // NOLINT - (cp < 0x03 || cp > 0x05) && cp != 0x0b && cp != 0x11 && - (cp < 0x13 || cp > 0x17) && cp != 0x19 && - (cp < 0x1c || cp > 0x1e) && - (cp < 0xd800 || cp > 0xdfff) && - (cp < 0x00040000 || cp >= 0x000e0000) - )) { - continue; - } + for (uint32_t cp = i; cp < 0x00110000; cp += nthread) { + //if (!( // NOLINT + // (cp < 0x03 || cp > 0x05) && cp != 0x0b && cp != 0x11 && + // (cp < 0x13 || cp > 0x17) && cp != 0x19 && + // (cp < 0x1c || cp > 0x1e) && + // (cp < 0xd800 || cp > 0xdfff) && + // (cp < 0x00040000 || cp >= 0x000e0000) + // )) { + // continue; + //} std::string str = unicode_cpt_to_utf8(cp); std::vector tokens = llama_tokenize(ctx, str, false); diff --git a/tests/test-tokenizer-1-spm.cpp b/tests/test-tokenizer-1-spm.cpp index cb37b4880..9f3d8d148 100644 --- a/tests/test-tokenizer-1-spm.cpp +++ b/tests/test-tokenizer-1-spm.cpp @@ -80,10 +80,10 @@ int main(int argc, char ** argv) { for (int i = 0; i < nthread; ++i) { threads[i] = std::thread([i, nthread, ctx]() { - for (uint32_t cp = i; cp < 0x0010ffff; cp += nthread) { - if (cp >= 0xd800 && cp <= 0xdfff) { - continue; - } + for (uint32_t cp = i; cp < 0x00110000; cp += nthread) { + //if (cp >= 0xd800 && cp <= 0xdfff) { + // continue; + //} std::string str = unicode_cpt_to_utf8(cp); std::vector tokens = llama_tokenize(ctx, str, false, true);