biogpt-customized-dataset / tokenizer_config.json

trained biogpt ner classification on customized dataset

2c12315 about 2 months ago

No virus

227 Bytes

	{
	"bos_token": "<s>",
	"clean_up_tokenization_spaces": true,
	"eos_token": "</s>",
	"model_max_length": 1024,
	"pad_token": "<pad>",
	"sep_token": "</s>",
	"tokenizer_class": "BioGptTokenizer",
	"unk_token": "<unk>"
	}