Upload tokenizer
Browse files- tokenizer_config.json +2 -8
tokenizer_config.json
CHANGED
|
@@ -2,7 +2,6 @@
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
"cls_token": "<s>",
|
| 5 |
-
"do_lower_case": true,
|
| 6 |
"eos_token": "</s>",
|
| 7 |
"mask_token": {
|
| 8 |
"__type": "AddedToken",
|
|
@@ -12,17 +11,12 @@
|
|
| 12 |
"rstrip": false,
|
| 13 |
"single_word": false
|
| 14 |
},
|
| 15 |
-
"max_length":
|
| 16 |
"model_max_length": 512,
|
| 17 |
-
"pad_to_multiple_of": null,
|
| 18 |
"pad_token": "<pad>",
|
| 19 |
-
"pad_token_type_id": 0,
|
| 20 |
-
"padding_side": "right",
|
| 21 |
"sep_token": "</s>",
|
| 22 |
"stride": 0,
|
| 23 |
-
"
|
| 24 |
-
"tokenize_chinese_chars": true,
|
| 25 |
-
"tokenizer_class": "BertTokenizer",
|
| 26 |
"truncation_side": "right",
|
| 27 |
"truncation_strategy": "longest_first",
|
| 28 |
"unk_token": "<unk>"
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
"cls_token": "<s>",
|
|
|
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"mask_token": {
|
| 7 |
"__type": "AddedToken",
|
|
|
|
| 11 |
"rstrip": false,
|
| 12 |
"single_word": false
|
| 13 |
},
|
| 14 |
+
"max_length": 256,
|
| 15 |
"model_max_length": 512,
|
|
|
|
| 16 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 17 |
"sep_token": "</s>",
|
| 18 |
"stride": 0,
|
| 19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
|
|
| 20 |
"truncation_side": "right",
|
| 21 |
"truncation_strategy": "longest_first",
|
| 22 |
"unk_token": "<unk>"
|