CODER-TAS-B / tokenizer_config.json
gzerveas's picture
add tokenizer
229f931
{"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": "sebastian-hofstaetter/distilbert-dot-tas_b-b256-msmarco", "special_tokens_map_file": "/users/gzerveas/.cache/huggingface/transformers/ba1a276969ccad7ea2344196e7b8561b36292db74bff940ee316dadc05d005d3.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_class": "DistilBertTokenizer"}