llama.cpp/unicode.cpp
jaime-m-p 43248e5594
llama3 custom regex split (#6965)
* 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

* llama3 custom regex split

* 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

* Using char32_t for codepoints

* lint : fix

* already exists unicode_tolower()

* Typing

* Restore BOM

* 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

* Fix merge

* 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

* Move unused variable value

* GPT2 custom regex split

* Add alternative regex for custom aplit llama3

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Style

* Add bruteforce random tests for token encoding

* wip: fixing unicode codepoint ranges

* Fix merge

* Unicode tables: separator, lowercase, uppercase and whitespace

* llama3 custom regex split: fix \s

* Restore BOM

* Style

* wip: generate NDF table

* Ignore special tokens for testing

* Clean gen-unicode-data.py

* Refactor random tokenizer test

* lint : fix

* tests : add fail test for llama-bpe

---------

Co-authored-by: Jaggzh <jaggz.h@gmail.com>
Co-authored-by: Kazim Abrar Mahi <kazimabrarmahi135@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: jaime-m-p <>
2024-05-09 23:30:44 +10:00

819 lines
30 KiB
C++

#include "unicode.h"
#include "unicode-data.h"
#include <cassert>
#include <cstddef>
#include <cstdint>
#include <map>
#include <regex>
#include <stdexcept>
#include <string>
#include <unordered_map>
#include <unordered_set>
#include <utility>
#include <vector>
#include <locale>
#include <codecvt>
static std::string unicode_cpts_to_utf8(const std::vector<uint32_t> & cps) {
std::string result;
for (size_t i = 0; i < cps.size(); ++i) {
result.append(unicode_cpt_to_utf8(cps[i]));
}
return result;
}
static uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset) {
assert(offset < utf8.size());
if (!(utf8[offset + 0] & 0x80)) {
auto result = utf8[offset + 0];
offset += 1;
return result;
}
if (!(utf8[offset + 0] & 0x40)) {
throw std::invalid_argument("invalid character");
}
if (!(utf8[offset + 0] & 0x20)) {
if (offset + 1 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80)) {
throw std::invalid_argument("invalid character");
}
auto result = ((utf8[offset + 0] & 0x1f) << 6) | (utf8[offset + 1] & 0x3f);
offset += 2;
return result;
}
if (!(utf8[offset + 0] & 0x10)) {
if (offset + 2 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80) || ! ((utf8[offset + 2] & 0xc0) == 0x80)) {
throw std::invalid_argument("invalid character");
}
auto result = ((utf8[offset + 0] & 0x0f) << 12) | ((utf8[offset + 1] & 0x3f) << 6) | (utf8[offset + 2] & 0x3f);
offset += 3;
return result;
}
if (!(utf8[offset + 0] & 0x08)) {
if (offset + 3 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80) || ! ((utf8[offset + 2] & 0xc0) == 0x80) || !((utf8[offset + 3] & 0xc0) == 0x80)) {
throw std::invalid_argument("invalid character");
}
auto result = ((utf8[offset + 0] & 0x07) << 18) | ((utf8[offset + 1] & 0x3f) << 12) | ((utf8[offset + 2] & 0x3f) << 6) | (utf8[offset + 3] & 0x3f);
offset += 4;
return result;
}
throw std::invalid_argument("failed to convert utf8 to codepoint");
}
//static std::vector<uint16_t> unicode_cpt_to_utf16(uint32_t cp) {
// std::vector<uint16_t> result;
// if (/* 0x0000 <= cp && */ cp <= 0xffff) {
// result.emplace_back(cp);
// return result;
// }
// if (0x10000 <= cp && cp <= 0x10ffff) {
// result.emplace_back(0xd800 | ((cp - 0x10000) >> 10));
// result.emplace_back(0xdc00 | ((cp - 0x10000) & 0x03ff));
// return result;
// }
// throw std::invalid_argument("failed to convert codepoint to utf16");
//}
//static std::vector<uint16_t> unicode_cpts_to_utf16(const std::vector<uint32_t> & cps) {
// std::vector<uint16_t> result;
// for (size_t i = 0; i < cps.size(); ++i) {
// auto temp = unicode_cpt_to_utf16(cps[i]);
// result.insert(result.end(), temp.begin(), temp.end());
// }
// return result;
//}
//static uint32_t unicode_cpt_from_utf16(const std::vector<uint16_t> & utf16, size_t & offset) {
// assert(offset < utf16.size());
// if (((utf16[0] >> 10) << 10) != 0xd800) {
// auto result = utf16[offset + 0];
// offset += 1;
// return result;
// }
//
// if (offset + 1 >= utf16.size() || !((utf16[1] & 0xdc00) == 0xdc00)) {
// throw std::invalid_argument("invalid character");
// }
//
// auto result = 0x10000 + (((utf16[0] & 0x03ff) << 10) | (utf16[1] & 0x03ff));
// offset += 2;
// return result;
//}
//static std::vector<uint32_t> unicode_cpts_from_utf16(const std::vector<uint16_t> & utf16) {
// std::vector<uint32_t> result;
// size_t offset = 0;
// while (offset < utf16.size()) {
// result.push_back(unicode_cpt_from_utf16(utf16, offset));
// }
// return result;
//}
static std::unordered_map<uint32_t, int> unicode_cpt_type_map() {
std::unordered_map<uint32_t, int> cpt_types;
for (auto p : unicode_ranges_number) {
for (auto i = p.first; i <= p.second; ++i) {
cpt_types[i] = CODEPOINT_TYPE_NUMBER;
}
}
for (auto p : unicode_ranges_letter) {
for (auto i = p.first; i <= p.second; ++i) {
cpt_types[i] = CODEPOINT_TYPE_LETTER;
}
}
for (auto p : unicode_ranges_separator) {
for (auto i = p.first; i <= p.second; ++i) {
cpt_types[i] = CODEPOINT_TYPE_SEPARATOR;
}
}
for (auto p : unicode_ranges_accent_mark) {
for (auto i = p.first; i <= p.second; ++i) {
cpt_types[i] = CODEPOINT_TYPE_ACCENT_MARK;
}
}
for (auto p : unicode_ranges_punctuation) {
for (auto i = p.first; i <= p.second; ++i) {
cpt_types[i] = CODEPOINT_TYPE_PUNCTUATION;
}
}
for (auto p : unicode_ranges_symbol) {
for (auto i = p.first; i <= p.second; ++i) {
cpt_types[i] = CODEPOINT_TYPE_SYMBOL;
}
}
for (auto p : unicode_ranges_control) {
for (auto i = p.first; i <= p.second; ++i) {
cpt_types[i] = CODEPOINT_TYPE_CONTROL;
}
}
return cpt_types;
}
static std::unordered_map<uint8_t, std::string> unicode_byte_to_utf8_map() {
std::unordered_map<uint8_t, std::string> map;
for (int ch = u'!'; ch <= u'~'; ++ch) {
assert(0 <= ch && ch < 256);
map[ch] = unicode_cpt_to_utf8(ch);
}
for (int ch = u'¡'; ch <= u'¬'; ++ch) {
assert(0 <= ch && ch < 256);
map[ch] = unicode_cpt_to_utf8(ch);
}
for (int ch = u'®'; ch <= u'ÿ'; ++ch) {
assert(0 <= ch && ch < 256);
map[ch] = unicode_cpt_to_utf8(ch);
}
auto n = 0;
for (int ch = 0; ch < 256; ++ch) {
if (map.find(ch) == map.end()) {
map[ch] = unicode_cpt_to_utf8(256 + n);
++n;
}
}
return map;
}
static std::unordered_map<std::string, uint8_t> unicode_utf8_to_byte_map() {
std::unordered_map<std::string, uint8_t> map;
for (int ch = u'!'; ch <= u'~'; ++ch) {
assert(0 <= ch && ch < 256);
map[unicode_cpt_to_utf8(ch)] = ch;
}
for (int ch = u'¡'; ch <= u'¬'; ++ch) {
assert(0 <= ch && ch < 256);
map[unicode_cpt_to_utf8(ch)] = ch;
}
for (int ch = u'®'; ch <= u'ÿ'; ++ch) {
assert(0 <= ch && ch < 256);
map[unicode_cpt_to_utf8(ch)] = ch;
}
auto n = 0;
for (int ch = 0; ch < 256; ++ch) {
if (map.find(unicode_cpt_to_utf8(ch)) == map.end()) {
map[unicode_cpt_to_utf8(256 + n)] = ch;
++n;
}
}
return map;
}
static inline std::wstring unicode_wstring_from_utf8(const std::string & s) {
std::wstring_convert<std::codecvt_utf8<wchar_t>> conv;
return conv.from_bytes(s);
}
static std::vector<std::string> unicode_byte_encoding_process(const std::vector<std::string> & bpe_words) {
std::vector<std::string> bpe_encoded_words;
for (const auto & word : bpe_words) {
std::string text_utf;
auto utf_word = unicode_cpts_from_utf8(word);
for (size_t i = 0; i < utf_word.size(); ++i) {
text_utf += unicode_cpt_to_utf8(utf_word[i]);
}
std::string encoded_token;
for (char & c : text_utf) {
encoded_token += unicode_byte_to_utf8(c);
}
bpe_encoded_words.emplace_back(encoded_token);
}
return bpe_encoded_words;
}
// GPT2 system regex: 's|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+
static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & text, const std::vector<size_t> & offsets) {
std::vector<size_t> bpe_offsets; // store the offset of each word
bpe_offsets.reserve(offsets.size()); // Reserve memory for the approximate size
const auto cpts = unicode_cpts_from_utf8(text);
size_t start = 0;
for (auto offset : offsets) {
const size_t offset_ini = start;
const size_t offset_end = start + offset;
assert(offset_end <= cpts.size());
start = offset_end;
auto _get_cpt = [&] (const size_t pos) -> char32_t {
return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : 0;
};
auto _get_cpt_type = [&] (const size_t pos) -> int {
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_type(cpts[pos]) : CODEPOINT_TYPE_UNIDENTIFIED;
};
size_t _prev_end = offset_ini;
auto _add_token = [&] (const size_t end) -> size_t {
assert(_prev_end <= end && end <= offset_end);
size_t len = end - _prev_end;
if (len > 0) {
bpe_offsets.push_back(len);
}
_prev_end = end;
//if (len > 0) {
// std::string s = "";
// for(size_t p = end-len; p < end; p++)
// s += unicode_cpt_to_utf8(cpts[p]);
// printf(">>> '%s'\n", s.c_str());
//}
return len;
};
for (size_t pos = offset_ini; pos < offset_end; /*pos++*/ ) {
const char32_t cpt = _get_cpt(pos);
const int cpt_type = _get_cpt_type(pos);
// regex: 's|'t|'re|'ve|'m|'ll|'d
if (cpt == '\'' && pos+1 < offset_end) {
char32_t cpt_next = _get_cpt(pos+1);
if (cpt_next == 's' || cpt_next == 't' || cpt_next == 'm' || cpt_next == 'd') {
pos += _add_token(pos+2);
continue;
}
if (pos+2 < offset_end) {
char32_t cpt_next_next = _get_cpt(pos+2);
if ((cpt_next == 'r' && cpt_next_next == 'e') ||
(cpt_next == 'v' && cpt_next_next == 'e') ||
(cpt_next == 'l' && cpt_next_next == 'l')) {
pos += _add_token(pos+3);
continue;
}
}
}
char32_t cpt2 = (cpt == ' ' ? _get_cpt(pos+1) : cpt);
int cpt2_type = (cpt == ' ' ? _get_cpt_type(pos+1) : cpt_type);
// regex: <space>?\p{L}+
if (cpt2_type == CODEPOINT_TYPE_LETTER) {
pos += (cpt == ' ');
while (cpt2_type == CODEPOINT_TYPE_LETTER) {
cpt2_type = _get_cpt_type(++pos);
}
_add_token(pos);
continue;
}
// regex: <space>?\p{N}+
if (cpt2_type == CODEPOINT_TYPE_NUMBER) {
pos += (cpt == ' ');
while (cpt2_type == CODEPOINT_TYPE_NUMBER) {
cpt2_type = _get_cpt_type(++pos);
}
_add_token(pos);
continue;
}
// regex: <space>?[^\s\p{L}\p{N}]+
if (!unicode_cpt_is_whitespace(cpt2) && cpt2_type != CODEPOINT_TYPE_LETTER && cpt2_type != CODEPOINT_TYPE_NUMBER && cpt2_type != CODEPOINT_TYPE_UNIDENTIFIED) {
pos += (cpt == ' ');
while (!unicode_cpt_is_whitespace(cpt2) && cpt2_type != CODEPOINT_TYPE_LETTER && cpt2_type != CODEPOINT_TYPE_NUMBER && cpt2_type != CODEPOINT_TYPE_UNIDENTIFIED) {
cpt2_type = _get_cpt_type(++pos);
cpt2 = _get_cpt(pos);
}
_add_token(pos);
continue;
}
size_t num_whitespaces = 0;
while (unicode_cpt_is_whitespace(_get_cpt(pos+num_whitespaces))) {
num_whitespaces++;
}
// regex: \s+(?!\S)
if (num_whitespaces > 1 && _get_cpt(pos+num_whitespaces) != 0) {
pos += num_whitespaces - 1;
_add_token(pos);
continue;
}
// regex: \s+
if (num_whitespaces > 0) {
pos += num_whitespaces;
_add_token(pos);
continue;
}
// no matches
_add_token(++pos);
}
}
return bpe_offsets;
}
// LLAMA3 system regex: "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}{1,3}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"
static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string & text, const std::vector<size_t> & offsets) {
std::vector<size_t> bpe_offsets; // store the offset of each word
bpe_offsets.reserve(offsets.size()); // Reserve memory for the approximate size
const auto cpts = unicode_cpts_from_utf8(text);
size_t start = 0;
for (auto offset : offsets) {
const size_t offset_ini = start;
const size_t offset_end = start + offset;
assert(offset_end <= cpts.size());
start = offset_end;
auto _get_cpt = [&] (const size_t pos) -> char32_t {
return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : 0;
};
auto _get_cpt_type = [&] (const size_t pos) -> int {
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_type(cpts[pos]) : CODEPOINT_TYPE_UNIDENTIFIED;
};
size_t _prev_end = offset_ini;
auto _add_token = [&] (const size_t end) -> size_t {
assert(_prev_end <= end && end <= offset_end);
size_t len = end - _prev_end;
if (len > 0) {
bpe_offsets.push_back(len);
}
_prev_end = end;
//if (len > 0) {
// std::string s = "";
// for(size_t p = end-len; p < end; p++)
// s += unicode_cpt_to_utf8(cpts[p]);
// printf(">>> '%s'\n", s.c_str());
//}
return len;
};
for (size_t pos = offset_ini; pos < offset_end; /*pos++*/ ) {
const char32_t cpt = _get_cpt(pos);
const int cpt_type = _get_cpt_type(pos);
// regex: (?i:'s|'t|'re|'ve|'m|'ll|'d) // case insensitive
if (cpt == '\'' && pos+1 < offset_end) {
char32_t cpt_next = unicode_tolower(_get_cpt(pos+1));
if (cpt_next == 's' || cpt_next == 't' || cpt_next == 'm' || cpt_next == 'd') {
pos += _add_token(pos+2);
continue;
}
if (pos+2 < offset_end) {
char32_t cpt_next_next = unicode_tolower(_get_cpt(pos+2));
if ((cpt_next == 'r' && cpt_next_next == 'e') ||
(cpt_next == 'v' && cpt_next_next == 'e') ||
(cpt_next == 'l' && cpt_next_next == 'l')) {
pos += _add_token(pos+3);
continue;
}
}
}
// regex: [^\r\n\p{L}\p{N}]?\p{L}+ //####FIXME: the first \p{L} is correct?
if (cpt != '\r' && cpt != '\n' && /*cpt_type != CODEPOINT_TYPE_LETTER &&*/ cpt_type != CODEPOINT_TYPE_NUMBER) {
if (cpt_type == CODEPOINT_TYPE_LETTER || _get_cpt_type(pos+1) == CODEPOINT_TYPE_LETTER) { // one or more letters
pos++;
while (_get_cpt_type(pos) == CODEPOINT_TYPE_LETTER) {
pos++;
}
_add_token(pos);
continue;
}
}
// regex: \p{N}{1,3}
if (cpt_type == CODEPOINT_TYPE_NUMBER) {
size_t ini = pos;
while (_get_cpt_type(pos) == CODEPOINT_TYPE_NUMBER) {
if (++pos - ini >= 3 ) {
_add_token(pos);
ini = pos;
}
}
_add_token(pos);
continue;
}
// regex: <space>?[^\s\p{L}\p{N}]+[\r\n]*
char32_t cpt2 = (cpt == ' ' ? _get_cpt(pos+1) : cpt);
int cpt2_type = (cpt == ' ' ? _get_cpt_type(pos+1) : cpt_type);
if (!unicode_cpt_is_whitespace(cpt2) && cpt2_type != CODEPOINT_TYPE_LETTER && cpt2_type != CODEPOINT_TYPE_NUMBER && cpt2_type != CODEPOINT_TYPE_UNIDENTIFIED) {
pos += (cpt == ' ');
while (!unicode_cpt_is_whitespace(cpt2) && cpt2_type != CODEPOINT_TYPE_LETTER && cpt2_type != CODEPOINT_TYPE_NUMBER && cpt2_type != CODEPOINT_TYPE_UNIDENTIFIED) {
cpt2_type = _get_cpt_type(++pos);
cpt2 = _get_cpt(pos);
}
while (cpt2 == '\r' || cpt2 == '\n') {
cpt2 = _get_cpt(++pos);
}
_add_token(pos);
continue;
}
size_t num_whitespaces = 0;
size_t last_end_r_or_n = 0;
while (unicode_cpt_is_whitespace(_get_cpt(pos+num_whitespaces))) {
char32_t cpt2 = _get_cpt(pos+num_whitespaces);
if (cpt2 == '\r' || cpt2 == '\n') {
last_end_r_or_n = pos + num_whitespaces + 1;
}
num_whitespaces++;
}
// regex: \s*[\r\n]+
if (last_end_r_or_n > 0) {
pos = last_end_r_or_n;
_add_token(pos);
continue;
}
// regex: \s+(?!\S)
if (num_whitespaces > 1 && _get_cpt(pos+num_whitespaces) != 0) {
pos += num_whitespaces - 1;
_add_token(pos);
continue;
}
// regex: \s+
if (num_whitespaces > 0) {
pos += num_whitespaces;
_add_token(pos);
continue;
}
// no matches
_add_token(++pos);
}
}
return bpe_offsets;
}
// use std::wregex to split the text
static std::vector<size_t> unicode_regex_split_stl(const std::wstring & wtext, const std::wstring & regex_expr, const std::vector<size_t> & offsets) {
std::wregex expr(regex_expr);
std::vector<size_t> bpe_offsets; // store the offset of each word
bpe_offsets.reserve(offsets.size()); // Reserve memory for the approximate size
size_t start = 0;
for (auto offset : offsets) {
std::wcregex_iterator it(wtext.data() + start, wtext.data() + start + offset, expr);
std::wcregex_iterator end;
int64_t start_idx = 0;
while (it != end) {
std::wcmatch match = *it;
if (match.position() > start_idx) {
bpe_offsets.emplace_back(match.position() - start_idx);
}
bpe_offsets.emplace_back(match.length());
start_idx = match.position() + match.length();
++it;
}
if (start_idx < (int64_t) offset) {
bpe_offsets.emplace_back(offset - start_idx);
}
start += offset;
}
return bpe_offsets;
}
// use std::regex to split the text
static std::vector<size_t> unicode_regex_split_stl(const std::string & text, const std::string & regex_expr, const std::vector<size_t> & offsets) {
std::regex expr(regex_expr);
std::vector<size_t> bpe_offsets; // store the offset of each word
bpe_offsets.reserve(offsets.size()); // Reserve memory for the approximate size
size_t start = 0;
for (auto offset : offsets) {
std::cregex_iterator it(text.data() + start, text.data() + start + offset, expr);
std::cregex_iterator end;
int64_t start_idx = 0;
while (it != end) {
std::cmatch match = *it;
if (match.position() > start_idx) {
bpe_offsets.emplace_back(match.position() - start_idx);
}
bpe_offsets.emplace_back(match.length());
start_idx = match.position() + match.length();
++it;
}
if (start_idx < (int64_t) offset) {
bpe_offsets.emplace_back(offset - start_idx);
}
start += offset;
}
return bpe_offsets;
}
static std::vector<size_t> unicode_regex_split_custom(const std::string & text, const std::string & regex_expr, const std::vector<size_t> & offsets) {
std::vector<size_t> bpe_offsets;
if (regex_expr == "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)") {
bpe_offsets = unicode_regex_split_custom_gpt2(text, offsets);
} else if (
regex_expr == "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+" ||
regex_expr == "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+") {
bpe_offsets = unicode_regex_split_custom_llama3(text, offsets);
}
return bpe_offsets;
}
//
// interface
//
std::string unicode_cpt_to_utf8(uint32_t cp) {
std::string result;
if (/* 0x00 <= cp && */ cp <= 0x7f) {
result.push_back(cp);
return result;
}
if (0x80 <= cp && cp <= 0x7ff) {
result.push_back(0xc0 | ((cp >> 6) & 0x1f));
result.push_back(0x80 | (cp & 0x3f));
return result;
}
if (0x800 <= cp && cp <= 0xffff) {
result.push_back(0xe0 | ((cp >> 12) & 0x0f));
result.push_back(0x80 | ((cp >> 6) & 0x3f));
result.push_back(0x80 | (cp & 0x3f));
return result;
}
if (0x10000 <= cp && cp <= 0x10ffff) {
result.push_back(0xf0 | ((cp >> 18) & 0x07));
result.push_back(0x80 | ((cp >> 12) & 0x3f));
result.push_back(0x80 | ((cp >> 6) & 0x3f));
result.push_back(0x80 | (cp & 0x3f));
return result;
}
throw std::invalid_argument("invalid codepoint");
}
std::vector<uint32_t> unicode_cpts_normalize_nfd(const std::vector<uint32_t> & cpts) {
std::vector<uint32_t> result;
result.reserve(cpts.size());
for (size_t i = 0; i < cpts.size(); ++i) {
auto it = unicode_map_nfd.find(cpts[i]);
if (it == unicode_map_nfd.end()) {
result.push_back(cpts[i]);
} else {
result.push_back(it->second);
}
}
return result;
}
std::vector<uint32_t> unicode_cpts_from_utf8(const std::string & utf8) {
std::vector<uint32_t> result;
size_t offset = 0;
while (offset < utf8.size()) {
result.push_back(unicode_cpt_from_utf8(utf8, offset));
}
return result;
}
int unicode_cpt_type(uint32_t cp) {
static std::unordered_map<uint32_t, int> cpt_types = unicode_cpt_type_map();
const auto it = cpt_types.find(cp);
return it == cpt_types.end() ? CODEPOINT_TYPE_UNIDENTIFIED : it->second;
}
int unicode_cpt_type(const std::string & utf8) {
if (utf8.length() == 0) {
return CODEPOINT_TYPE_UNIDENTIFIED;
}
size_t offset = 0;
return unicode_cpt_type(unicode_cpt_from_utf8(utf8, offset));
}
bool unicode_cpt_is_whitespace(uint32_t cp) {
static const std::unordered_set<uint32_t> is_whitespace = [] {
std::unordered_set<uint32_t> is_whitespace;
for (auto p : unicode_ranges_whitespace) {
for (auto i = p.first; i <= p.second; ++i) {
is_whitespace.insert(i);
}
}
return is_whitespace;
}();
return (bool)is_whitespace.count(cp);
}
std::string unicode_byte_to_utf8(uint8_t byte) {
static std::unordered_map<uint8_t, std::string> map = unicode_byte_to_utf8_map();
return map.at(byte);
}
uint8_t unicode_utf8_to_byte(const std::string & utf8) {
static std::unordered_map<std::string, uint8_t> map = unicode_utf8_to_byte_map();
return map.at(utf8);
}
char32_t unicode_tolower(char32_t cp) {
auto it = unicode_map_lowercase.find(cp);
return it == unicode_map_lowercase.end() ? cp : it->second;
}
std::vector<std::string> unicode_regex_split(const std::string & text, const std::vector<std::string> & regex_exprs) {
// unicode categories
static const std::map<std::string, int> k_ucat_enum = {
{ "\\p{N}", CODEPOINT_TYPE_NUMBER },
{ "\\p{L}", CODEPOINT_TYPE_LETTER },
{ "\\p{P}", CODEPOINT_TYPE_PUNCTUATION },
};
static const std::map<int, int> k_ucat_cpt = {
{ CODEPOINT_TYPE_NUMBER, 0xD1 },
{ CODEPOINT_TYPE_LETTER, 0xD2 },
{ CODEPOINT_TYPE_PUNCTUATION, 0xD3 },
};
static const std::map<int, std::string> k_ucat_map = {
{ CODEPOINT_TYPE_NUMBER, "\x30-\x39" }, // 0-9
{ CODEPOINT_TYPE_LETTER, "\x41-\x5A\x61-\x7A" }, // A-Za-z
{ CODEPOINT_TYPE_PUNCTUATION, "\x21-\x23\x25-\x2A\x2C-\x2F\x3A-\x3B\x3F-\x40\\\x5B-\\\x5D\x5F\\\x7B\\\x7D" }, // !-#%-*,-/:-;?-@\[-\]_\{\}
};
// compute collapsed codepoints only if needed by at least one regex
bool need_collapse = false;
for (auto & regex_expr : regex_exprs) {
// search for unicode categories
for (const auto & ucat : k_ucat_enum) {
if (std::string::npos != regex_expr.find(ucat.first)) {
need_collapse = true;
break;
}
}
}
const auto cpts = unicode_cpts_from_utf8(text);
// generate a "collapsed" representation of the text, where all codepoints are replaced by a single byte
// ref: https://github.com/ggerganov/llama.cpp/pull/6920#issuecomment-2081479935
std::string text_collapsed;
if (need_collapse) {
// collapse all unicode categories
text_collapsed.resize(cpts.size());
for (size_t i = 0; i < cpts.size(); ++i) {
// keep single-byte codepoints as is
if (cpts[i] < 128) {
text_collapsed[i] = cpts[i];
continue;
}
const int cpt_type = unicode_cpt_type(cpts[i]);
if (k_ucat_cpt.find(cpt_type) != k_ucat_cpt.end()) {
text_collapsed[i] = k_ucat_cpt.at(cpt_type);
} else {
text_collapsed[i] = (char) 0xD0; // fallback
}
}
}
std::vector<size_t> bpe_offsets = { cpts.size() };
for (auto & regex_expr : regex_exprs) {
// first, see if we have an efficient custom regex implementation
auto tmp = unicode_regex_split_custom(text, regex_expr, bpe_offsets);
if (!tmp.empty()) {
bpe_offsets = std::move(tmp);
continue;
}
// fallback to general-purpose std::regex / std::wregex
try {
// if a unicode category is used in the regex, we use the collapsed text and replace the unicode category
// with the corresponding collapsed representation
bool use_collapsed = false;
for (auto & ucat : k_ucat_enum) {
if (std::string::npos != regex_expr.find(ucat.first)) {
use_collapsed = true;
break;
}
}
if (use_collapsed) {
// sanity-check that the original regex does not contain any non-ASCII characters
const auto cpts_regex = unicode_cpts_from_utf8(regex_expr);
for (size_t i = 0; i < cpts_regex.size(); ++i) {
if (cpts_regex[i] >= 128) {
throw std::runtime_error("Regex includes both unicode categories and non-ASCII characters - not supported");
}
}
// generate a collapsed representation of the regex
std::string regex_expr_collapsed;
// track if we are inside [], because nested [] are not allowed
bool inside = false;
for (size_t i = 0; i < regex_expr.size(); ++i) {
if (regex_expr[i] == '[' && (i == 0 || regex_expr[i - 1] != '\\')) {
regex_expr_collapsed += '[';
inside = true;
continue;
}
if (inside && regex_expr[i] == ']' && regex_expr[i - 1] != '\\') {
regex_expr_collapsed += ']';
inside = false;
continue;
}
if (regex_expr[i + 0] == '\\' && i + 4 < regex_expr.size() &&
regex_expr[i + 1] == 'p' &&
regex_expr[i + 2] == '{' &&
regex_expr[i + 4] == '}') {
const std::string pat = regex_expr.substr(i, 5);
if (k_ucat_enum.find(pat) != k_ucat_enum.end()) {
if (!inside) {
regex_expr_collapsed += '[';
}
regex_expr_collapsed += k_ucat_cpt.at(k_ucat_enum.at(pat));
regex_expr_collapsed += k_ucat_map.at(k_ucat_enum.at(pat));
if (!inside) {
regex_expr_collapsed += ']';
}
i += 4;
continue;
}
}
regex_expr_collapsed += regex_expr[i];
}
//printf("text_collapsed: %s\n", text_collapsed.c_str());
//printf("regex_expr_collapsed: %s\n", regex_expr_collapsed.c_str());
bpe_offsets = unicode_regex_split_stl(text_collapsed, regex_expr_collapsed, bpe_offsets);
} else {
// no unicode category used, we can use std::wregex directly
const std::wstring wtext = unicode_wstring_from_utf8(text);
const std::wstring wregex_expr = unicode_wstring_from_utf8(regex_expr);
//printf("text: %s\n", text.c_str());
//printf("regex_expr: %s\n", regex_expr.c_str());
bpe_offsets = unicode_regex_split_stl(wtext, wregex_expr, bpe_offsets);
}
} catch (std::regex_error & e) {
fprintf(stderr, "Failed to process regex: '%s'\n", regex_expr.c_str());
fprintf(stderr, "Regex error: %s\n", e.what());
throw std::runtime_error("Failed to process regex");
}
}
std::vector<std::string> bpe_words;
bpe_words.reserve(bpe_offsets.size()); // reserve memory for the approximate size
size_t start = 0;
for (size_t & offset : bpe_offsets) {
bpe_words.emplace_back();
for (size_t i = start; i < start + offset; ++i) {
bpe_words.back() += unicode_cpt_to_utf8(cpts[i]);
}
start += offset;
}
return unicode_byte_encoding_process(bpe_words);
}