Upload tokenizer
Browse files- special_tokens_map.json +35 -5
- tokenizer_config.json +1 -2
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,37 @@
|
|
| 1 |
{
|
| 2 |
-
"cls_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "<cls>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<eos>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"mask_token": {
|
| 17 |
+
"content": "<mask>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "<pad>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "<unk>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
}
|
tokenizer_config.json
CHANGED
|
@@ -41,11 +41,10 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"backend": "custom",
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "<cls>",
|
| 47 |
"eos_token": "<eos>",
|
| 48 |
-
"
|
| 49 |
"mask_token": "<mask>",
|
| 50 |
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
"pad_token": "<pad>",
|
|
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
|
|
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "<cls>",
|
| 46 |
"eos_token": "<eos>",
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
"mask_token": "<mask>",
|
| 49 |
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
"pad_token": "<pad>",
|