jishnunair
commited on
Commit
•
93b0f2b
1
Parent(s):
0e50a1f
Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +4 -0
tokenizer_config.json
CHANGED
@@ -45,11 +45,15 @@
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": false,
|
47 |
"mask_token": "[MASK]",
|
|
|
48 |
"model_max_length": 512,
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
|
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
"tokenizer_class": "DistilBertTokenizer",
|
|
|
|
|
54 |
"unk_token": "[UNK]"
|
55 |
}
|
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": false,
|
47 |
"mask_token": "[MASK]",
|
48 |
+
"max_length": 512,
|
49 |
"model_max_length": 512,
|
50 |
"pad_token": "[PAD]",
|
51 |
"sep_token": "[SEP]",
|
52 |
+
"stride": 0,
|
53 |
"strip_accents": null,
|
54 |
"tokenize_chinese_chars": true,
|
55 |
"tokenizer_class": "DistilBertTokenizer",
|
56 |
+
"truncation_side": "right",
|
57 |
+
"truncation_strategy": "longest_first",
|
58 |
"unk_token": "[UNK]"
|
59 |
}
|