bart-base-chinese / tokenizer_config.json
yunfan
update model to version 2.0
4e93f21
raw
history blame
479 Bytes
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "bos_token": "[CLS]", "eos_token": "[EOS]", "name_or_path": "/remote-home/yfshao/workdir/code-base/Megatron-LM/init_models_ckpt/bart_zh/base", "special_tokens_map_file": "vocab/cpt_v3_vocab/special_tokens_map.json", "tokenizer_file": null}