gpt2-base-ptt / tokenizer_config.json
voidful's picture
update model
bab494b
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "eos_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "ckiplab/gpt2-base-chinese", "do_basic_tokenize": true, "never_split": null}