CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Detokenizer fixes (#8039)

Browse Source 
* Add llama_detokenize():
  - Update header files location
  - UNKNOWN and CONTROL are 'special pieces'
  - Remove space after UNKNOWN and CONTROL
  - Refactor llama_token_to_piece()
  - Add flag: clean_up_tokenization_spaces
  - Symmetric params for llama_tokenize() and llama_detokenize()

* Update and fix tokenizer tests:
  - Using llama_detokenize()
  - Unexpected vocab type as test fail instead of error
    - Useful when automating tests:
    - If you don't know in advance the vocab type
    - Differenciate other loading errors
  - Skip unicode surrogaes and undefined
  - Gracefully exit threads
    - Using exit() is throwing random exceptions
  - Clean old known problematic codepoints
  - Minor: confusing hexadecimal codepoint

* Update bruteforce random tests
  - Add detokenizer checks
  - New generator: ascii_lr_strip
  - New generator: apostrophe
  - Add more vocabs files
  - Detokenize special tokens.
  - Replace errors with '\uFFFD' when detokenizing to 'utf-8'
  - More edge cases
  - Better detokenization results check

* Fix add_space_prefix, set false by default
* Better leading space removal
* Do not remove space when decoding special tokens
* Bugfix: custom regexs splits undefined unicode codepoints
* 'viking' detokenizer clean spaces
This commit is contained in:
jaime-m-p
2024-07-05 19:01:35 +02:00
committed by GitHub
parent be20e7f49d
commit 213701b51a
11 changed files with 499 additions and 265 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
tests/test-tokenizer-1-bpe.cpp
View File

@@ -11,6 +11,7 @@
#include <string>
#include <thread>
#include <vector>
#include <atomic>
int main(int argc, char **argv) {
if (argc < 2 || argc > 3) {
@@ -63,7 +64,10 @@ int main(int argc, char **argv) {
}
}
GGML_ASSERT(llama_vocab_type(model) == LLAMA_VOCAB_TYPE_BPE);
//GGML_ASSERT(llama_vocab_type(model) == LLAMA_VOCAB_TYPE_BPE);
if (llama_vocab_type(model) != LLAMA_VOCAB_TYPE_BPE) {
return 99;
}
#ifdef _WIN32
// We need this for unicode console support
@@ -74,7 +78,7 @@ int main(int argc, char **argv) {
const int n_vocab = llama_n_vocab(model);
for (int i = 0; i < n_vocab; ++i) {
std::string str = llama_detokenize_bpe(ctx, std::vector<int>(1, i));
std::string str = llama_detokenize(ctx, std::vector<int>(1, i));
try {
auto cps = unicode_cpts_from_utf8(str);
std::vector<llama_token> tokens = llama_tokenize(ctx, str, false, true);
@@ -90,7 +94,7 @@ int main(int argc, char **argv) {
fprintf(stderr, "]\n");
return 2;
}
std::string check = llama_detokenize_bpe(ctx, tokens);
std::string check = llama_detokenize(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());
@@ -108,26 +112,23 @@ int main(int argc, char **argv) {
std::vector<std::thread> threads(nthread);
std::atomic_int errcode = {};
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)
)) {
threads[i] = std::thread([i, nthread, ctx, &errcode]() {
for (uint32_t cp = i; !errcode && cp < 0x00110000; cp += nthread) {
if ((0x0000D800 <= cp && cp <= 0x0000DFFF) || // surrogates \p{Cs}
(0x00040000 <= cp && cp <= 0x000E0000)) { // undefined \p{Cn}
continue;
}
std::string str = unicode_cpt_to_utf8(cp);
std::vector<llama_token> tokens = llama_tokenize(ctx, str, false);
std::string check = llama_detokenize_bpe(ctx, tokens);
std::string check = llama_detokenize(ctx, tokens);
if (cp != 9601 && str != check) {
fprintf(stderr, "error: codepoint %x detokenizes to '%s'(%zu) instead of '%s'(%zu)\n",
fprintf(stderr, "error: codepoint 0x%x detokenizes to '%s'(%zu) instead of '%s'(%zu)\n",
cp, check.c_str(), check.length(), str.c_str(), str.length());
std::exit(3);
errcode = 3;
}
}
});
@@ -136,6 +137,10 @@ int main(int argc, char **argv) {
for (auto & t : threads) {
t.join();
}
if (errcode) {
return errcode;
}
}
llama_free_model(model);