Theivaprakasham commited on
Commit
8c293a5
1 Parent(s): 54e42f8

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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "name_or_path": "sentence-transformers/msmarco-distilbert-base-tas-b", "special_tokens_map_file": "/home/ukp-reimers/.cache/huggingface/transformers/ba1a276969ccad7ea2344196e7b8561b36292db74bff940ee316dadc05d005d3.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_class": "DistilBertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff