hierarchical-transformer-I3-mini-1024 / tokenizer_config.json
kiddothe2b
Initial commit
c2ba13f
raw
history blame
489 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, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "data/PLMs/hi-transformer-s2-grouped", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer", "auto_map": {"AutoTokenizer": ["tokenization_hat.HATTokenizer", "tokenization_hat.HATTokenizer"]}}