hankgreen / tokenizer_config.json

New model from https://wandb.ai/wandb/huggingtweets/runs/jb24l8bp

f6e59fa about 1 year ago

No virus

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\|>"
	}