polyglot / tokenizer_config.json

Upload tokenizer_config.json

d8c071a verified over 2 years ago

210 Bytes

{
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "PreTrainedTokenizerFast"
}

	{
	"clean_up_tokenization_spaces": true,
	"eos_token": "<\|endoftext\|>",
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<\|endoftext\|>",
	"tokenizer_class": "PreTrainedTokenizerFast"
	}