Tung177
/

sentence-splitting

Text2Text Generation

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

sentence-splitting / tokenizer_config.json

Tung177's picture

Training in progress, epoch 0

d9b066d 7 months ago

raw history blame contribute delete

No virus

1.2 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": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"40029": {
	"content": "<mask>",
	"lstrip": true,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"bos_token": "<s>",
	"clean_up_tokenization_spaces": true,
	"cls_token": "<s>",
	"eos_token": "</s>",
	"mask_token": "<mask>",
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<pad>",
	"sep_token": "</s>",
	"sp_model_kwargs": {},
	"tokenizer_class": "BartphoTokenizer",
	"unk_token": "<unk>"
	}