optimum-intel-internal-testing
/

ov-tiny-random-distilbert

Text Classification

text-embeddings-inference

Model card Files Files and versions

ov-tiny-random-distilbert / tokenizer_config.json

IlyasMoutawwakil's picture

IlyasMoutawwakil HF Staff

Upload tokenizer

ace08c0 verified 6 months ago

history blame contribute delete

1.22 kB

	{
	"added_tokens_decoder": {
	"0": {
	"content": "[PAD]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "[UNK]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "[CLS]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"3": {
	"content": "[SEP]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"4": {
	"content": "[MASK]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"clean_up_tokenization_spaces": false,
	"cls_token": "[CLS]",
	"do_lower_case": true,
	"extra_special_tokens": {},
	"mask_token": "[MASK]",
	"model_max_length": 512,
	"pad_token": "[PAD]",
	"sep_token": "[SEP]",
	"strip_accents": null,
	"tokenize_chinese_chars": true,
	"tokenizer_class": "DistilBertTokenizer",
	"unk_token": "[UNK]"
	}