From eb34620aeceaf9d9df7fcb19acc17ad41b9f60f8 Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Tue, 21 Mar 2023 17:29:41 +0200
Subject: Add tokenizer test + revert to C++11 (#355)

* Add test-tokenizer-0 to do a few tokenizations - feel free to expand
* Added option to convert-pth-to-ggml.py script to dump just the vocabulary
* Added ./models/ggml-vocab.bin containing just LLaMA vocab data (used for tests)
* Added utility to load vocabulary file from previous point (temporary implementation)
* Avoid using std::string_view and drop back to C++11 (hope I didn't break something)
* Rename gpt_vocab -> llama_vocab
* All CMake binaries go into ./bin/ now
---
 tests/CMakeLists.txt       |  4 +++
 tests/test-tokenizer-0.cpp | 69 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 73 insertions(+)
 create mode 100644 tests/CMakeLists.txt
 create mode 100644 tests/test-tokenizer-0.cpp

(limited to 'tests')

diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt
new file mode 100644
index 0000000..a2c1e3f
--- /dev/null
+++ b/tests/CMakeLists.txt
@@ -0,0 +1,4 @@
+set(TEST_TARGET test-tokenizer-0)
+add_executable(${TEST_TARGET} ${TEST_TARGET}.cpp)
+target_link_libraries(${TEST_TARGET} PRIVATE utils)
+add_test(NAME ${TEST_TARGET} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab.bin)
diff --git a/tests/test-tokenizer-0.cpp b/tests/test-tokenizer-0.cpp
new file mode 100644
index 0000000..6bc49f2
--- /dev/null
+++ b/tests/test-tokenizer-0.cpp
@@ -0,0 +1,69 @@
+#include "utils.h"
+
+#include <cstdio>
+#include <string>
+#include <map>
+
+static const std::map<std::string, std::vector<llama_vocab::id>> k_tests = {
+    { "Hello World",        { 1,  10994,   2787, }, },
+    { " Hello World",       { 1,  15043,   2787, }, },
+    { " Hello World!",      { 1,  15043,   2787,  29991, }, },
+    { " this is 🦙.cpp",    { 1,    445,    338,  29871,    243,    162,    169,    156,  29889,   8223, }, },
+    { "w048 7tuijk dsdfhu", { 1,  29893,  29900,  29946,  29947,  29871,  29955,   9161,  13535,  18031,   2176,   6905, }, },
+    { "нещо на Български",  { 1,    821,   4851,    665,   1386,  29713,   1305, }, },
+};
+
+int main(int argc, char **argv) {
+    if (argc < 2) {
+        fprintf(stderr, "Usage: %s <vocab-file>\n", argv[0]);
+        return 1;
+    }
+
+    const std::string fname = argv[1];
+
+    fprintf(stderr, "%s : reading vocab from: '%s'\n", __func__, fname.c_str());
+
+    llama_vocab vocab;
+
+    if (!llama_vocab_load(fname, vocab)) {
+        fprintf(stderr, "%s : failed to load vocab from: '%s'\n", __func__, fname.c_str());
+        return 1;
+    }
+
+    const int n_vocab = vocab.id_to_token.size();
+
+    if (n_vocab != 32000) {
+        fprintf(stderr, "%s : expected 32000 tokens, got %d\n", __func__, n_vocab);
+        return 2;
+    }
+
+    for (const auto & test_kv : k_tests) {
+        const auto res = llama_tokenize(vocab, test_kv.first, true);
+
+        bool correct = res.size() == test_kv.second.size();
+
+        for (int i = 0; i < (int) res.size() && correct; ++i) {
+            if (res[i] != test_kv.second[i]) {
+                correct = false;
+            }
+        }
+
+        if (!correct) {
+            fprintf(stderr, "%s : failed test: '%s'\n", __func__, test_kv.first.c_str());
+            fprintf(stderr, "%s : expected tokens: ", __func__);
+            for (const auto & t : test_kv.second) {
+                fprintf(stderr, "%6d, ", t);
+            }
+            fprintf(stderr, "\n");
+            fprintf(stderr, "%s : got tokens:      ", __func__);
+            for (const auto & t : res) {
+                fprintf(stderr, "%6d, ", t);
+            }
+            fprintf(stderr, "\n");
+
+            return 3;
+        }
+    }
+
+    return 0;
+}
-- 
cgit v1.2.3