MichelBartels commited on
Commit
3b4adf2
1 Parent(s): 2ea9f86
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +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": "outputs/ponet-base-uncased", "tokenizer_class": "BertTokenizer", "model_input_names": ["input_ids", "token_type_ids", "attention_mask", "segment_ids"]}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff