Upload tokenizer
Browse files- special_tokens_map.json +5 -13
- tokenizer.json +0 -0
- tokenizer_config.json +10 -62
- vocab.txt +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,15 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
|
| 7 |
-
"lstrip": true,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
-
"pad_token": "<pad>",
|
| 13 |
-
"sep_token": "</s>",
|
| 14 |
-
"unk_token": "<unk>"
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,65 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": {
|
| 4 |
-
"__type": "AddedToken",
|
| 5 |
-
"content": "<s>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": true,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false
|
| 10 |
-
},
|
| 11 |
"clean_up_tokenization_spaces": true,
|
| 12 |
-
"cls_token":
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
"
|
| 21 |
-
|
| 22 |
-
"content": "</s>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": true,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false
|
| 27 |
-
},
|
| 28 |
-
"errors": "replace",
|
| 29 |
-
"mask_token": {
|
| 30 |
-
"__type": "AddedToken",
|
| 31 |
-
"content": "<mask>",
|
| 32 |
-
"lstrip": true,
|
| 33 |
-
"normalized": true,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false
|
| 36 |
-
},
|
| 37 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
-
"num_labels": 3,
|
| 39 |
-
"pad_token": {
|
| 40 |
-
"__type": "AddedToken",
|
| 41 |
-
"content": "<pad>",
|
| 42 |
-
"lstrip": false,
|
| 43 |
-
"normalized": true,
|
| 44 |
-
"rstrip": false,
|
| 45 |
-
"single_word": false
|
| 46 |
-
},
|
| 47 |
-
"sep_token": {
|
| 48 |
-
"__type": "AddedToken",
|
| 49 |
-
"content": "</s>",
|
| 50 |
-
"lstrip": false,
|
| 51 |
-
"normalized": true,
|
| 52 |
-
"rstrip": false,
|
| 53 |
-
"single_word": false
|
| 54 |
-
},
|
| 55 |
-
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
-
"trim_offsets": true,
|
| 57 |
-
"unk_token": {
|
| 58 |
-
"__type": "AddedToken",
|
| 59 |
-
"content": "<unk>",
|
| 60 |
-
"lstrip": false,
|
| 61 |
-
"normalized": true,
|
| 62 |
-
"rstrip": false,
|
| 63 |
-
"single_word": false
|
| 64 |
-
}
|
| 65 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "BertTokenizer",
|
| 12 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|