Upload tokenizer
Browse files- tokenizer_config.json +8 -3
tokenizer_config.json
CHANGED
@@ -43,11 +43,16 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
-
"do_basic_tokenize":
|
47 |
-
"do_lower_case":
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 1000000000000000019884624838656,
|
50 |
-
"never_split":
|
|
|
|
|
|
|
|
|
|
|
51 |
"pad_token": "[PAD]",
|
52 |
"sep_token": "[SEP]",
|
53 |
"strip_accents": null,
|
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": false,
|
47 |
+
"do_lower_case": false,
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": [
|
51 |
+
"A",
|
52 |
+
"U",
|
53 |
+
"G",
|
54 |
+
"C"
|
55 |
+
],
|
56 |
"pad_token": "[PAD]",
|
57 |
"sep_token": "[SEP]",
|
58 |
"strip_accents": null,
|