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

Add alternative regex for custom aplit llama3

Browse source 
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
jaime-m-p 2024-04-30 13:02:46 +02:00 • committed by GitHub
parent 1d8fcc06ba
commit 2cd1eb0daa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
unicode.cpp
View file

@ -532,7 +532,10 @@ static std::vector<size_t> unicode_regex_split_custom(const std::string & text,
if (regex_expr == "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)") { 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); 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+") { } 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); bpe_offsets = unicode_regex_split_custom_llama3(text, offsets);
} }