schihei/llama2.c
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

minimal protection against invalid UTF8 encoding.

Browse Source
This commit is contained in:
rdentato
2023-08-16 07:42:53 +00:00
parent ca67253f28
commit befe4867b3
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
run.c
+3 -1
View File
@@ -396,7 +396,8 @@ void bpe_encode(char *text, char **vocab, float *vocab_scores, int vocab_size, u
str_buffer[str_len] = '\0'; str_buffer[str_len] = '\0';
// while the next character is a continuation byte, continue appending // while the next character is a continuation byte, continue appending
if ((*(c+1) & 0xC0) == 0x80) { // but if there are too many of them, just stop to avoid overruning str_buffer size.
if ((*(c+1) & 0xC0) == 0x80 && str_len < 4) {
continue; continue;
} }
@@ -414,6 +415,7 @@ void bpe_encode(char *text, char **vocab, float *vocab_scores, int vocab_size, u
tokens[(*n_tokens)++] = (unsigned char)str_buffer[i] + 3; tokens[(*n_tokens)++] = (unsigned char)str_buffer[i] + 3;
} }
} }
str_len = 0; // protect against a sequence of stray UTF8 continuation bytes
} }
// merge the best consecutive pair each iteration, according the scores in vocab_scores // merge the best consecutive pair each iteration, according the scores in vocab_scores