public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-02 12:31:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2026-05-02 15:02:42 +03:00
parent 18162bcf61
commit 4bf733672b
144 changed files with 3675 additions and 5535 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/unicode.cpp
+175 -3
View File
@@ -470,6 +470,141 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
return bpe_offsets;
}
// Qwen2 system regex: "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
static std::vector<size_t> unicode_regex_split_custom_qwen2(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;
static const uint32_t OUT_OF_RANGE = 0xFFFFFFFF;
auto _get_cpt = [&] (const size_t pos) -> uint32_t {
return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : OUT_OF_RANGE;
};
auto _get_flags = [&] (const size_t pos) -> unicode_cpt_flags {
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags_from_cpt(cpts[pos]) : unicode_cpt_flags{};
};
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 uint32_t cpt = _get_cpt(pos);
const auto flags = _get_flags(pos);
// regex: (?i:'s|'t|'re|'ve|'m|'ll|'d) // case insensitive
if (cpt == '\'' && pos+1 < offset_end) {
uint32_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) {
uint32_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}+
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) {
pos++;
}
_add_token(pos);
continue;
}
}
// regex: \p{N}
if (flags.is_number) {
pos++;
_add_token(pos);
continue;
}
// 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) && flags.as_uint()) {
pos += (cpt == ' ');
while (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
flags2 = _get_flags(++pos);
}
uint32_t 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 (_get_flags(pos+num_whitespaces).is_whitespace) {
uint32_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) != OUT_OF_RANGE) {
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;
}
template <typename CharT>
static std::vector<size_t> unicode_regex_split_stl(const std::basic_string<CharT> & text, const std::basic_string<CharT> & regex, const std::vector<size_t> & offsets) {
using BidirIt = typename std::basic_string<CharT>::const_iterator;
@@ -753,6 +888,35 @@ static std::vector<size_t> unicode_regex_split_custom_afmoe(const std::string &
return bpe_offsets;
}
// regex: [^\n]+|[\n]+
// splits text into runs of non-newline characters and runs of newline characters
static std::vector<size_t> unicode_regex_split_custom_newlines(const std::string & text, const std::vector<size_t> & offsets) {
std::vector<size_t> bpe_offsets;
bpe_offsets.reserve(offsets.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;
size_t pos = offset_ini;
while (pos < offset_end) {
const bool is_newline = (cpts[pos] == '\n');
const size_t run_start = pos;
while (pos < offset_end && (cpts[pos] == '\n') == is_newline) {
pos++;
}
bpe_offsets.push_back(pos - run_start);
}
}
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;
@@ -761,14 +925,18 @@ static std::vector<size_t> unicode_regex_split_custom(const std::string & text,
} 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);
} else if (
regex_expr == "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+") {
bpe_offsets = unicode_regex_split_custom_qwen2(text, offsets);
} else if (regex_expr == "\\p{Han}+") {
// K2's first pattern - handle all K2 patterns together
bpe_offsets = unicode_regex_split_custom_kimi_k2(text, offsets);
} else if (regex_expr == "\\p{AFMoE_digits}") {
// AFMOE digit pattern - use custom implementation for proper splitting
bpe_offsets = unicode_regex_split_custom_afmoe(text, offsets);
} else if (regex_expr == "[^\\n]+|[\\n]+") {
bpe_offsets = unicode_regex_split_custom_newlines(text, offsets);
} else if (regex_expr == "\\d{1,3}(?=(?:\\d{3})*\\b)") {
// tiny_aya digit grouping pattern from tokenizer.json:
// {"type": "Split", "pattern": {"Regex": "\\d{1,3}(?=(?:\\d{3})*\\b)"}, "behavior": "Isolated"}
@@ -912,7 +1080,7 @@ bool unicode_cpt_is_han(uint32_t cpt) {
return false;
}
std::vector<std::string> unicode_regex_split(const std::string & text, const std::vector<std::string> & regex_exprs) {
std::vector<std::string> unicode_regex_split(const std::string & text, const std::vector<std::string> & regex_exprs, bool byte_encode) {
// unicode categories
static const std::map<std::string, int> k_ucat_enum = {
{ "\\p{N}", unicode_cpt_flags::NUMBER },
@@ -1099,5 +1267,9 @@ std::vector<std::string> unicode_regex_split(const std::string & text, const std
start += offset;
}
return unicode_byte_encoding_process(bpe_words);
if (byte_encode) {
return unicode_byte_encoding_process(bpe_words);
}
return bpe_words;
}