Upload tokenizer
Browse files- README.md +1 -1
- tokenizer_config.json +2 -0
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
base_model: bert-base-uncased
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
1 |
---
|
|
|
2 |
base_model: bert-base-uncased
|
3 |
+
license: apache-2.0
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
tokenizer_config.json
CHANGED
@@ -43,9 +43,11 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
|
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
"model_max_length": 512,
|
|
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
"pad_token": "[PAD]",
|
52 |
"sep_token": "[SEP]",
|
53 |
"strip_accents": null,
|