Upload tokenizer
Browse files- tokenizer.json +11 -1
- tokenizer_config.json +2 -1
tokenizer.json
CHANGED
|
@@ -58,7 +58,17 @@
|
|
| 58 |
"trim_offsets": true,
|
| 59 |
"use_regex": true
|
| 60 |
},
|
| 61 |
-
"post_processor":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
"decoder": {
|
| 63 |
"type": "ByteLevel",
|
| 64 |
"add_prefix_space": true,
|
|
|
|
| 58 |
"trim_offsets": true,
|
| 59 |
"use_regex": true
|
| 60 |
},
|
| 61 |
+
"post_processor": {
|
| 62 |
+
"type": "BertProcessing",
|
| 63 |
+
"sep": [
|
| 64 |
+
"[SEP]",
|
| 65 |
+
2
|
| 66 |
+
],
|
| 67 |
+
"cls": [
|
| 68 |
+
"[CLS]",
|
| 69 |
+
1
|
| 70 |
+
]
|
| 71 |
+
},
|
| 72 |
"decoder": {
|
| 73 |
"type": "ByteLevel",
|
| 74 |
"add_prefix_space": true,
|
tokenizer_config.json
CHANGED
|
@@ -43,10 +43,11 @@
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
|
|
|
| 46 |
"mask_token": "[MASK]",
|
| 47 |
"model_max_length": 8192,
|
| 48 |
"pad_token": "[PAD]",
|
| 49 |
"sep_token": "[SEP]",
|
| 50 |
-
"tokenizer_class": "
|
| 51 |
"unk_token": "[UNK]"
|
| 52 |
}
|
|
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
+
"extra_special_tokens": {},
|
| 47 |
"mask_token": "[MASK]",
|
| 48 |
"model_max_length": 8192,
|
| 49 |
"pad_token": "[PAD]",
|
| 50 |
"sep_token": "[SEP]",
|
| 51 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 52 |
"unk_token": "[UNK]"
|
| 53 |
}
|