AI-Sweden-Models
/

gpt-sw3-20b-instruct-4bit-gptq

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

gpt-sw3-20b-instruct-4bit-gptq / generation_config.json

nicher92's picture

Upload model

01a76a8 about 1 year ago

159 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 2,
	"eos_token_id": 3,
	"max_length": 2048,
	"pad_token_id": 0,
	"transformers_version": "4.36.0.dev0"
	}