cert-contrasitive-embedding / tokenizer_config.json

Upload 9 files

c958c71 verified 8 months ago

618 Bytes

{
  "backend": "tokenizers",
  "bos_token": "[CLS]",
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": false,
  "eos_token": "[SEP]",
  "is_local": false,
  "mask_token": "[MASK]",
  "max_length": 128,
  "model_max_length": 128,
  "never_split": null,
  "pad_to_multiple_of": null,
  "pad_token": "[PAD]",
  "pad_token_type_id": 0,
  "padding_side": "right",
  "sep_token": "[SEP]",
  "stride": 0,
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "TokenizersBackend",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "[UNK]"
}

	{
	"backend": "tokenizers",
	"bos_token": "[CLS]",
	"cls_token": "[CLS]",
	"do_basic_tokenize": true,
	"do_lower_case": false,
	"eos_token": "[SEP]",
	"is_local": false,
	"mask_token": "[MASK]",
	"max_length": 128,
	"model_max_length": 128,
	"never_split": null,
	"pad_to_multiple_of": null,
	"pad_token": "[PAD]",
	"pad_token_type_id": 0,
	"padding_side": "right",
	"sep_token": "[SEP]",
	"stride": 0,
	"strip_accents": null,
	"tokenize_chinese_chars": true,
	"tokenizer_class": "TokenizersBackend",
	"truncation_side": "right",
	"truncation_strategy": "longest_first",
	"unk_token": "[UNK]"
	}