xverse
/

XVERSE-13B-Chat-GPTQ-Int8

Text Generation

8-bit precision

Model card Files Files and versions Community

XVERSE-13B-Chat-GPTQ-Int8 / tokenizer_config.json

willhe-xverse's picture

Upload folder using huggingface_hub

532b134 verified 3 months ago

raw history blame contribute delete

No virus

146 Bytes

	{
	"clean_up_tokenization_spaces": true,
	"model_max_length": 1000000000000000019884624838656,
	"tokenizer_class": "PreTrainedTokenizerFast"
	}