Abzu
/

mpt-7b-storywriter-q8

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions Community

mpt-7b-storywriter-q8 / tokenizer_config.json

Danivilanova's picture

Upload folder using huggingface_hub

300c59d 11 months ago

raw history blame contribute delete

No virus

238 Bytes

	{
	"add_prefix_space": false,
	"bos_token": "<\|endoftext\|>",
	"clean_up_tokenization_spaces": true,
	"eos_token": "<\|endoftext\|>",
	"model_max_length": 65536,
	"tokenizer_class": "GPTNeoXTokenizer",
	"unk_token": "<\|endoftext\|>"
	}