thu-coai
/

roberta-zh-specific

Text Classification Transformers PyTorch Safetensors Chinese bert Conversational Inference Endpoints

Model card Files Files and versions Community

roberta-zh-specific / tokenizer_config.json

everk's picture

Upload tokenizer

1c9b36b over 1 year ago

raw history blame contribute delete

No virus

383 Bytes

	{
	"cls_token": "[CLS]",
	"do_basic_tokenize": true,
	"do_lower_case": true,
	"mask_token": "[MASK]",
	"name_or_path": "/data/songyi/eva/9-14/spec/",
	"never_split": null,
	"pad_token": "[PAD]",
	"sep_token": "[SEP]",
	"special_tokens_map_file": null,
	"strip_accents": null,
	"tokenize_chinese_chars": true,
	"tokenizer_class": "BertTokenizer",
	"unk_token": "[UNK]"
	}