llama : fix BPE pre-tokenization (#6920)

* merged the changes from deepseeker models to main branch * Moved regex patterns to unicode.cpp and updated unicode.h * Moved header files * Resolved issues * added and refactored unicode_regex_split and related functions * Updated/merged the deepseek coder pr * Refactored code * Adding unicode regex mappings * Adding unicode regex function * Added needed functionality, testing remains * Fixed issues * Fixed issue with gpt2 regex custom preprocessor * unicode : fix? unicode_wstring_to_utf8 * lint : fix whitespaces * tests : add tokenizer tests for numbers * unicode : remove redundant headers * tests : remove and rename tokenizer test scripts * tests : add sample usage * gguf-py : reader prints warnings on duplicate keys * llama : towards llama3 tokenization support (wip) * unicode : shot in the dark to fix tests on Windows * unicode : first try custom implementations * convert : add "tokenizer.ggml.pre" GGUF KV (wip) * llama : use new pre-tokenizer type * convert : fix pre-tokenizer type writing * lint : fix * make : add test-tokenizer-0-llama-v3 * wip * models : add llama v3 vocab file * llama : adapt punctuation regex + add llama 3 regex * minor * unicode : set bomb * unicode : set bomb * unicode : always use std::wregex * unicode : support \p{N}, \p{L} and \p{P} natively * unicode : try fix windows * unicode : category support via std::regex * unicode : clean-up * unicode : simplify * convert : add convert-hf-to-gguf-update.py ggml-ci * lint : update * convert : add falcon ggml-ci * unicode : normalize signatures * lint : fix * lint : fix * convert : remove unused functions * convert : add comments * convert : exercise contractions ggml-ci * lint : fix * cmake : refactor test targets * tests : refactor vocab tests ggml-ci * tests : add more vocabs and tests ggml-ci * unicode : cleanup * scripts : ignore new update script in check-requirements.sh * models : add phi-3, mpt, gpt-2, starcoder * tests : disable obsolete ggml-ci * tests : use faster bpe test ggml-ci * llama : more prominent warning for old BPE models * tests : disable test-tokenizer-1-bpe due to slowness ggml-ci --------- Co-authored-by: Jaggzh <jaggz.h@gmail.com> Co-authored-by: Kazim Abrar Mahi <kazimabrarmahi135@gmail.com>
2025-11-13 10:57:15 +00:00 · 2024-04-29 16:58:41 +03:00
parent 3f167476b1
commit f4ab2a4147
59 changed files with 2902 additions and 637 deletions
--- a/tests/test-tokenizer-1-spm.cpp
+++ b/tests/test-tokenizer-1-spm.cpp
@@ -0,0 +1,111 @@
+#include "llama.h"
+#include "common.h"
+#include "unicode.h"
+#include "console.h"
+
+#include <cassert>
+#include <codecvt>
+#include <cstdio>
+#include <cstring>
+#include <locale>
+#include <string>
+#include <thread>
+#include <vector>
+
+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_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;
+        }
+    }
+
+    GGML_ASSERT(llama_vocab_type(model) == LLAMA_VOCAB_TYPE_SPM);
+
+#ifdef _WIN32
+    // We need this for unicode console support
+    console::init(false, false);
+    atexit([]() { console::cleanup(); });
+#endif
+
+    const int n_vocab = llama_n_vocab(model);
+
+    for (int i = 0; i < n_vocab; ++i) {
+        std::string str = llama_detokenize_spm(ctx, std::vector<int>(1, i));
+        std::vector<llama_token> tokens = llama_tokenize(ctx, str, false);
+        std::string check = llama_detokenize_spm(ctx, tokens);
+        if (check != str) {
+            fprintf(stderr, "%s : error: token %d detokenizes to '%s'(%zu) but tokenization of this detokenizes to '%s'(%zu)\n",
+                __func__, i, str.c_str(), str.length(), check.c_str(), check.length());
+            return 2;
+        }
+    }
+
+    // unicode
+    {
+        const int nthread = std::thread::hardware_concurrency();
+
+        std::vector<std::thread> threads(nthread);
+
+        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;
+                    }
+
+                    std::string str = unicode_cpt_to_utf8(cp);
+                    std::vector<llama_token> tokens = llama_tokenize(ctx, str, false);
+                    std::string check = llama_detokenize_spm(ctx, tokens);
+                    if (cp != 9601 && str != check) {
+                        fprintf(stderr, "error: codepoint %x detokenizes to '%s'(%zu) instead of '%s'(%zu)\n",
+                                cp, check.c_str(), check.length(), str.c_str(), str.length());
+                        std::exit(3);
+                    }
+                }
+            });
+        }
+
+        for (auto & t : threads) {
+            t.join();
+        }
+    }
+
+    llama_free_model(model);
+    llama_free(ctx);
+
+    llama_backend_free();
+
+    return 0;
+}