Update tokenizer_config.json
Browse filesHard-code needed tokenization config
- tokenizer_config.json +6 -1
tokenizer_config.json
CHANGED
@@ -10,5 +10,10 @@
|
|
10 |
"strip_accents": null,
|
11 |
"tokenize_chinese_chars": true,
|
12 |
"tokenizer_class": "BertTokenizer",
|
13 |
-
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
14 |
}
|
|
|
10 |
"strip_accents": null,
|
11 |
"tokenize_chinese_chars": true,
|
12 |
"tokenizer_class": "BertTokenizer",
|
13 |
+
"unk_token": "[UNK]",
|
14 |
+
"return_tensors": "pt",
|
15 |
+
"max_length": 256,
|
16 |
+
"add_special_tokens": false,
|
17 |
+
"return_attention_mask": true,
|
18 |
+
"return_token_type_ids": false
|
19 |
}
|