Upload tokenizer
Browse files- special_tokens_map.json +0 -2
- tokenizer_config.json +1 -19
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
-
"eos_token": "</s>",
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"pad_token": "[PAD]",
|
| 7 |
"sep_token": "[SEP]",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
|
|
|
| 3 |
"mask_token": "[MASK]",
|
| 4 |
"pad_token": "[PAD]",
|
| 5 |
"sep_token": "[SEP]",
|
tokenizer_config.json
CHANGED
|
@@ -39,30 +39,12 @@
|
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
-
},
|
| 43 |
-
"911": {
|
| 44 |
-
"content": "<s>",
|
| 45 |
-
"lstrip": false,
|
| 46 |
-
"normalized": false,
|
| 47 |
-
"rstrip": false,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": true
|
| 50 |
-
},
|
| 51 |
-
"912": {
|
| 52 |
-
"content": "</s>",
|
| 53 |
-
"lstrip": false,
|
| 54 |
-
"normalized": false,
|
| 55 |
-
"rstrip": false,
|
| 56 |
-
"single_word": false,
|
| 57 |
-
"special": true
|
| 58 |
}
|
| 59 |
},
|
| 60 |
-
"bos_token": "<s>",
|
| 61 |
"clean_up_tokenization_spaces": true,
|
| 62 |
"cls_token": "[CLS]",
|
| 63 |
"do_basic_tokenize": true,
|
| 64 |
"do_lower_case": false,
|
| 65 |
-
"eos_token": "</s>",
|
| 66 |
"mask_token": "[MASK]",
|
| 67 |
"model_max_length": 1000000000000000019884624838656,
|
| 68 |
"never_split": null,
|
|
@@ -70,6 +52,6 @@
|
|
| 70 |
"sep_token": "[SEP]",
|
| 71 |
"strip_accents": null,
|
| 72 |
"tokenize_chinese_chars": true,
|
| 73 |
-
"tokenizer_class": "
|
| 74 |
"unk_token": "[UNK]"
|
| 75 |
}
|
|
|
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
}
|
| 43 |
},
|
|
|
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": false,
|
|
|
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
"never_split": null,
|
|
|
|
| 52 |
"sep_token": "[SEP]",
|
| 53 |
"strip_accents": null,
|
| 54 |
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "MobileBertTokenizer",
|
| 56 |
"unk_token": "[UNK]"
|
| 57 |
}
|