e5-small-v2 / tokenizer_config.json

Make the tokenizer config match that of the large and base versions (#11)

dca8b1a over 2 years ago

314 Bytes

	{
	"clean_up_tokenization_spaces": true,
	"cls_token": "[CLS]",
	"do_lower_case": true,
	"mask_token": "[MASK]",
	"model_max_length": 512,
	"pad_token": "[PAD]",
	"sep_token": "[SEP]",
	"strip_accents": null,
	"tokenize_chinese_chars": true,
	"tokenizer_class": "BertTokenizer",
	"unk_token": "[UNK]"
	}