Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +2 -1
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -43,10 +43,11 @@
|
|
| 43 |
}
|
| 44 |
},
|
| 45 |
"bos_token": "<s>",
|
| 46 |
-
"clean_up_tokenization_spaces":
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"errors": "replace",
|
|
|
|
| 50 |
"mask_token": "<mask>",
|
| 51 |
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
"pad_token": "<pad>",
|
|
|
|
| 43 |
}
|
| 44 |
},
|
| 45 |
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
"mask_token": "<mask>",
|
| 52 |
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
"pad_token": "<pad>",
|