Просмотр исходного кода

llama : use Unicode Escape Sequence to replace encoded characters (#2814)

The use of special characters within source files can break compiling on some computers with different region and language settings. Using Unicode escape sequences should allow for the code to be compiled on all setups without needing to change your computers settings or switch regions.
Tim Miller 2 лет назад
Родитель
Сommit
c7d92e6dfe
1 измененных файлов с 4 добавлено и 4 удалено
  1. 4 4
      llama.cpp

+ 4 - 4
llama.cpp

@@ -955,10 +955,10 @@ struct llama_vocab {
     id linefeed_id = 13;
 
     int find_bpe_rank(std::string token_left, std::string token_right) const {
-        replace_all(token_left,  " ",  "Ġ");
-        replace_all(token_left,  "\n", "Ċ");
-        replace_all(token_right, " ",  "Ġ");
-        replace_all(token_right, "\n", "Ċ");
+        replace_all(token_left,  " ",  "\u0120");
+        replace_all(token_left,  "\n", "\u010A");
+        replace_all(token_right, " ",  "\u0120");
+        replace_all(token_right, "\n", "\u010A");
 
         auto it = bpe_ranks.find(std::make_pair(token_left, token_right));
         if (it == bpe_ranks.end()) {