Upload tokenizer
Browse files- special_tokens_map.json +14 -0
- tokenizer_config.json +2 -0
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,11 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": {
|
| 3 |
"content": "[CLS]",
|
| 4 |
"lstrip": false,
|
|
@@ -6,6 +13,13 @@
|
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"mask_token": {
|
| 10 |
"content": "[MASK]",
|
| 11 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
"cls_token": {
|
| 10 |
"content": "[CLS]",
|
| 11 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"mask_token": {
|
| 24 |
"content": "[MASK]",
|
| 25 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -41,8 +41,10 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
|
|
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
|
|
|
| 46 |
"mask_token": "[MASK]",
|
| 47 |
"max_length": 500,
|
| 48 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 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 |
"max_length": 500,
|
| 50 |
"model_max_length": 1000000000000000019884624838656,
|