From 1d0521195dce48c26c122a71310faf1ed0c38d94 Mon Sep 17 00:00:00 2001 From: Niels Rogge Date: Wed, 19 Jan 2022 17:24:36 +0000 Subject: [PATCH] Update tokenizer_config.json --- tokenizer_config.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tokenizer_config.json b/tokenizer_config.json index f1f6a44..311bbad 100644 --- a/tokenizer_config.json +++ b/tokenizer_config.json @@ -1 +1 @@ -{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"} \ No newline at end of file +{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 40, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"} \ No newline at end of file