nlpai-lab
/

KURE-v2

Sentence Similarity

sentence-transformers

late-interaction

feature-extraction

text-embeddings-inference

Model card Files Files and versions

KURE-v2 / tokenizer_config.json

yjoonjang's picture

Initial commit

cd3f61c 9 days ago

History Blame Contribute Delete

600 Bytes

	{
	"backend": "tokenizers",
	"bos_token": "<s>",
	"clean_up_tokenization_spaces": true,
	"cls_token": "<cls>",
	"do_lower_case": false,
	"eos_token": "<\\s>",
	"is_local": true,
	"mask_token": "<mask>",
	"max_length": 255,
	"model_max_length": 255,
	"pad_to_multiple_of": null,
	"pad_token": "<mask>",
	"pad_token_type_id": 0,
	"padding_side": "right",
	"sep_token": "<sep>",
	"stride": 0,
	"strip_accents": null,
	"tokenize_chinese_chars": true,
	"tokenizer_class": "BertTokenizer",
	"truncation_side": "right",
	"truncation_strategy": "longest_first",
	"unk_token": "<unk>"
	}