Gaxys
/

MPnet-PD_Books

Text Classification

text-embeddings-inference

Model card Files Files and versions

Metrics Training metrics Community

MPnet-PD_Books / tokenizer_config.json

Gaxys's picture

Training in progress, step 500

dbcf57a almost 3 years ago

Raw History Blame Contribute Delete

1.39 kB

	{
	"added_tokens_decoder": {
	"0": {
	"content": "<s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<pad>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "</s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"3": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"104": {
	"content": "[UNK]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"30526": {
	"content": "<mask>",
	"lstrip": true,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"bos_token": "<s>",
	"clean_up_tokenization_spaces": true,
	"cls_token": "<s>",
	"do_lower_case": true,
	"eos_token": "</s>",
	"mask_token": "<mask>",
	"model_max_length": 512,
	"pad_token": "<pad>",
	"sep_token": "</s>",
	"strip_accents": null,
	"tokenize_chinese_chars": true,
	"tokenizer_class": "MPNetTokenizer",
	"unk_token": "[UNK]"
	}