Add tokenizer_config.json
Browse files- tokenizer_config.json +9 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "TypoTokenizer",
|
| 3 |
+
"model_type": "bpe",
|
| 4 |
+
"unk_token": "<unk>",
|
| 5 |
+
"bos_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"max_chars_per_token": 16
|
| 9 |
+
}
|