emrecan commited on
Commit
fa7354f
1 Parent(s): 7a6a0ce

add tokenizer

Browse files
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": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "dbmdz_distilbert-base-turkish-cased_multinli_tr", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "DistilBertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff