Upload tokenizer
Browse files- special_tokens_map.json +22 -1
- tokenizer.json +0 -0
- tokenizer_config.json +5 -10
special_tokens_map.json
CHANGED
|
@@ -6,6 +6,13 @@
|
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"eos_token": {
|
| 10 |
"content": "[SEP]",
|
| 11 |
"lstrip": false,
|
|
@@ -14,7 +21,7 @@
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"mask_token": {
|
| 17 |
-
"content": "MASK",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
@@ -26,5 +33,19 @@
|
|
| 26 |
"normalized": false,
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
}
|
| 30 |
}
|
|
|
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
"eos_token": {
|
| 17 |
"content": "[SEP]",
|
| 18 |
"lstrip": false,
|
|
|
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
"lstrip": false,
|
| 26 |
"normalized": false,
|
| 27 |
"rstrip": false,
|
|
|
|
| 33 |
"normalized": false,
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
}
|
| 51 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -39,21 +39,16 @@
|
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
-
},
|
| 43 |
-
"50000": {
|
| 44 |
-
"content": "MASK",
|
| 45 |
-
"lstrip": false,
|
| 46 |
-
"normalized": false,
|
| 47 |
-
"rstrip": false,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": true
|
| 50 |
}
|
| 51 |
},
|
| 52 |
"bos_token": "[CLS]",
|
| 53 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 54 |
"eos_token": "[SEP]",
|
| 55 |
-
"mask_token": "MASK",
|
| 56 |
"model_max_length": 1000000000000000019884624838656,
|
| 57 |
"pad_token": "[PAD]",
|
| 58 |
-
"
|
|
|
|
|
|
|
| 59 |
}
|
|
|
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
}
|
| 43 |
},
|
| 44 |
"bos_token": "[CLS]",
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
"eos_token": "[SEP]",
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 53 |
+
"unk_token": "[UNK]"
|
| 54 |
}
|