vivekraina
/

falcon-7b-8bit

Text Generation

RefinedWebModel

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

falcon-7b-8bit / generation_config.json

vivekraina's picture

Model quantized to 4 bits

ba05886 over 1 year ago

116 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.31.0.dev0"
	}