vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 499 additions and 265 deletions
Download patch file Download diff file Expand all files Collapse all files

58
common/common.cpp
View file

@ -2592,51 +2592,35 @@ std::vector<llama_token> llama_tokenize(
}
std::string llama_token_to_piece(const struct llama_context * ctx, llama_token token, bool special) {
std::vector<char> result(8, 0);
const int n_tokens = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size(), special);
if (n_tokens < 0) {
result.resize(-n_tokens);
int check = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size(), special);
GGML_ASSERT(check == -n_tokens);
} else {
result.resize(n_tokens);
std::string piece;
piece.resize(piece.capacity()); // using string internal cache, 15 bytes + '\n'
const int n_chars = llama_token_to_piece(llama_get_model(ctx), token, &piece[0], piece.size(), 0, special);
if (n_chars < 0) {
piece.resize(-n_chars);
int check = llama_token_to_piece(llama_get_model(ctx), token, &piece[0], piece.size(), 0, special);
GGML_ASSERT(check == -n_chars);
}
else {
piece.resize(n_chars);
}
return std::string(result.data(), result.size());
return piece;
}
std::string llama_detokenize_spm(llama_context * ctx, const std::vector<llama_token> & tokens) {
const llama_token bos_id = llama_token_bos(llama_get_model(ctx));
std::string piece;
std::string result;
for (size_t i = 0; i < tokens.size(); ++i) {
piece = llama_token_to_piece(ctx, tokens[i]);
// remove the leading space of the first non-BOS token
if (((tokens[0] == bos_id && i == 1) || (tokens[0] != bos_id && i == 0)) && piece[0] == ' ') {
piece = piece.substr(1);
}
result += piece;
std::string llama_detokenize(llama_context * ctx, const std::vector<llama_token> & tokens, bool special) {
std::string text;
text.resize(std::max(text.capacity(), tokens.size()));
int32_t n_chars = llama_detokenize(llama_get_model(ctx), tokens.data(), (int32_t)tokens.size(), &text[0], (int32_t)text.size(), false, special);
if (n_chars < 0) {
text.resize(-n_chars);
n_chars = llama_detokenize(llama_get_model(ctx), tokens.data(), (int32_t)tokens.size(), &text[0], (int32_t)text.size(), false, special);
GGML_ASSERT(n_chars <= (int32_t)text.size()); // whitespace trimming is performed after per-token detokenization
}
return result;
}
std::string llama_detokenize_bpe(llama_context * ctx, const std::vector<llama_token> & tokens) {
std::string piece;
std::string result;
for (size_t i = 0; i < tokens.size(); ++i) {
piece = llama_token_to_piece(ctx, tokens[i]);
result += piece;
}
text.resize(n_chars);
// NOTE: the original tokenizer decodes bytes after collecting the pieces.
return result;
return text;
}
bool llama_should_add_bos_token(const llama_model * model) {