mmarco-sentence-BERTino / tokenizer_config.json
efederici's picture
v1
91f1dc1
raw
history blame
395 Bytes
{"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, "max_len": 512, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "indigo-ai/BERTino", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "DistilBertTokenizer"}