Hezar: Upload tokenizer and config
Browse files
preprocessor/tokenizer.json
CHANGED
|
@@ -1119,6 +1119,7 @@
|
|
| 1119 |
"continuing_subword_prefix": "",
|
| 1120 |
"end_of_word_suffix": "",
|
| 1121 |
"fuse_unk": false,
|
|
|
|
| 1122 |
"vocab": {
|
| 1123 |
"!": 0,
|
| 1124 |
"\"": 1,
|
|
|
|
| 1119 |
"continuing_subword_prefix": "",
|
| 1120 |
"end_of_word_suffix": "",
|
| 1121 |
"fuse_unk": false,
|
| 1122 |
+
"byte_fallback": false,
|
| 1123 |
"vocab": {
|
| 1124 |
"!": 0,
|
| 1125 |
"\"": 1,
|