Skip to content

Commit 348c748

Browse files
authored
Add tekken to the tokenize tool (#119)
Differential Revision: D81692978 Pull Request resolved: #124
1 parent 05711be commit 348c748

File tree

1 file changed

+3
-0
lines changed

1 file changed

+3
-0
lines changed

examples/tokenize_tool/main.cpp

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,7 @@
2121
// Local
2222
#include "hf_tokenizer.h"
2323
#include "sentencepiece.h"
24+
#include "tekken.h"
2425
#include "tiktoken.h"
2526

2627
using namespace tokenizers;
@@ -64,6 +65,8 @@ int main(int argc, char* argv[]) {
6465
tok_ptr.reset(new Tiktoken());
6566
} else if (tokenizer_type == "hf_tokenizer") {
6667
tok_ptr.reset(new HFTokenizer());
68+
} else if (tokenizer_type == "tekken") {
69+
tok_ptr.reset(new Tekken());
6770
} else {
6871
std::stringstream ss;
6972
ss << "ERROR: Invalid tokenizer type: " << tokenizer_type << std::endl

0 commit comments

Comments
 (0)