Upload tokenizer
Browse files- added_tokens.json +7 -0
- tokenizer_config.json +47 -1
added_tokens.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[CLS]": 101,
|
| 3 |
+
"[MASK]": 103,
|
| 4 |
+
"[PAD]": 0,
|
| 5 |
+
"[SEP]": 102,
|
| 6 |
+
"[UNK]": 100
|
| 7 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -1,9 +1,55 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
|
|
|
| 4 |
"do_lower_case": true,
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
-
"model_max_length":
|
|
|
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
| 9 |
"strip_accents": null,
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "[PAD]",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"100": {
|
| 13 |
+
"content": "[UNK]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"101": {
|
| 21 |
+
"content": "[CLS]",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"102": {
|
| 29 |
+
"content": "[SEP]",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"103": {
|
| 37 |
+
"content": "[MASK]",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"additional_special_tokens": [],
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
"cls_token": "[CLS]",
|
| 48 |
+
"do_basic_tokenize": true,
|
| 49 |
"do_lower_case": true,
|
| 50 |
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
"pad_token": "[PAD]",
|
| 54 |
"sep_token": "[SEP]",
|
| 55 |
"strip_accents": null,
|