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

get rid of the special byte decoding logic

Browse Source
This commit is contained in:
Andrej Karpathy
2023-08-15 01:04:10 +00:00
parent 8417cb438d
commit 4bf36ecc17
1 changed files with 4 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
run.c
+3 -14
View File
@@ -440,19 +440,6 @@ void bpe_encode(char *text, char **vocab, float *vocab_scores, int vocab_size, u
free(sorted_vocab);
}
// convert token to printable string
char *token_to_str(char **vocab, int token, int prev_token) {
// following BOS (1) token, sentencepiece decoder strips any leading whitespace (see PR #89)
char *token_str = (prev_token == 1 && vocab[token][0] == ' ') ? vocab[token]+1 : vocab[token];
// make '<0x01>' into '\x01'
static char byte_piece[4];
if (sscanf(token_str, "<0x%02X>", (int*)(&byte_piece)) == 1) {
byte_piece[1] = '\0';
token_str = byte_piece;
}
return token_str;
}
// ----------------------------------------------------------------------------
// utilities: time / rng
@@ -699,7 +686,9 @@ int main(int argc, char *argv[]) {
// data-dependent terminating condition: the BOS (1) token delimits sequences
if (next == 1) { break; }
printf("%s", token_to_str(vocab, next, token));
// following BOS (1) token, sentencepiece decoder strips any leading whitespace (see PR #89)
char *token_str = (token == 1 && vocab[next][0] == ' ') ? vocab[next]+1 : vocab[next];
printf("%s", token_str);
fflush(stdout);
token = next;