avey-b-ur / tokenizer_config.json

Publish Avey-B Urdu 25M with benchmarks and model card

4cae2c2 verified about 2 months ago

268 Bytes

{
  "backend": "tokenizers",
  "cls_token": "[CLS]",
  "mask_token": "[MASK]",
  "model_max_length": 512,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "unk_token": "[UNK]",
  "clean_up_tokenization_spaces": false
}

	{
	"backend": "tokenizers",
	"cls_token": "[CLS]",
	"mask_token": "[MASK]",
	"model_max_length": 512,
	"pad_token": "[PAD]",
	"sep_token": "[SEP]",
	"tokenizer_class": "PreTrainedTokenizerFast",
	"unk_token": "[UNK]",
	"clean_up_tokenization_spaces": false
	}