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

18
src/unicode.cpp
View file

@ -232,8 +232,7 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & t
};
auto _get_flags = [&] (const size_t pos) -> codepoint_flags {
static const codepoint_flags undef(codepoint_flags::UNDEFINED);
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : undef;
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : codepoint_flags{};
};
size_t _prev_end = offset_ini;
@ -295,9 +294,9 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & t
continue;
}
// regex: <space>?[^\s\p{L}\p{N}]+
if (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
if (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
pos += (cpt == ' ');
while (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
while (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
flags2 = _get_flags(++pos);
}
_add_token(pos);
@ -351,8 +350,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
};
auto _get_flags = [&] (const size_t pos) -> codepoint_flags {
static const codepoint_flags undef(codepoint_flags::UNDEFINED);
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : undef;
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : codepoint_flags{};
};
size_t _prev_end = offset_ini;
@ -394,8 +392,8 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
}
}
// regex: [^\r\n\p{L}\p{N}]?\p{L}+ //####FIXME: the first \p{L} is correct?
if (!(cpt == '\r' || cpt == '\n' || /*flags.is_letter |*/ flags.is_number)) {
// regex: [^\r\n\p{L}\p{N}]?\p{L}+
if (!(cpt == '\r' || cpt == '\n' || flags.is_number)) {
if (flags.is_letter || _get_flags(pos+1).is_letter) { // one or more letters
pos++;
while (_get_flags(pos).is_letter) {
@ -421,9 +419,9 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
// regex: <space>?[^\s\p{L}\p{N}]+[\r\n]*
auto flags2 = (cpt == ' ' ? _get_flags(pos+1) : flags);
if (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
if (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags.as_uint()) {
pos += (cpt == ' ');
while (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
while (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
flags2 = _get_flags(++pos);
}
uint32_t cpt2 = _get_cpt(pos);