org-shared-embeddings / tokenizer_config.json

Matt Brady

Add POC stub

e9822ed verified 4 months ago

215 Bytes

{
  "do_lower_case": true,
  "model_max_length": 256,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "cls_token": "[CLS]",
  "unk_token": "[UNK]",
  "mask_token": "[MASK]",
  "tokenizer_class": "BertTokenizer"
}

	{
	"do_lower_case": true,
	"model_max_length": 256,
	"pad_token": "[PAD]",
	"sep_token": "[SEP]",
	"cls_token": "[CLS]",
	"unk_token": "[UNK]",
	"mask_token": "[MASK]",
	"tokenizer_class": "BertTokenizer"
	}