MartaSamoilenko
/

Mistral-7b-quantized-int8-bnb

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

Mistral-7b-quantized-int8-bnb / generation_config.json

MartaSamoilenko's picture

MartaSamoilenko

Upload 8 files

cb43591 verified almost 2 years ago

history blame contribute delete

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.38.2"
	}