gpt_small_rm / tokenizer_config.json

add tokenizer

cc9532c over 3 years ago

234 Bytes

{
  "add_prefix_space": false,
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "model_max_length": 1024,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}

	{
	"add_prefix_space": false,
	"bos_token": "<\|endoftext\|>",
	"clean_up_tokenization_spaces": true,
	"eos_token": "<\|endoftext\|>",
	"model_max_length": 1024,
	"tokenizer_class": "GPT2Tokenizer",
	"unk_token": "<\|endoftext\|>"
	}