vortex-tok-16k / tokenizer_config.json

english 16k tokenizer

4369317 verified 28 days ago

223 Bytes

{
  "tokenizer_class": "PreTrainedTokenizerFast",
  "bos_token": "<|bos|>",
  "eos_token": "<|eos|>",
  "pad_token": "<|pad|>",
  "unk_token": "<|unk|>",
  "clean_up_tokenization_spaces": false,
  "model_max_length": 2048
}

	{
	"tokenizer_class": "PreTrainedTokenizerFast",
	"bos_token": "<\|bos\|>",
	"eos_token": "<\|eos\|>",
	"pad_token": "<\|pad\|>",
	"unk_token": "<\|unk\|>",
	"clean_up_tokenization_spaces": false,
	"model_max_length": 2048
	}