TheBloke
/

h2ogpt-gm-oasst1-en-2048-falcon-7b-v3-GPTQ

Text Generation

RefinedWebModel

large language model

text-generation-inference

4-bit precision

Model card Files Files and versions Community

h2ogpt-gm-oasst1-en-2048-falcon-7b-v3-GPTQ / generation_config.json

TheBloke's picture

Initial GPTQ model commit

24c59b6 over 1 year ago

113 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 11,
	"eos_token_id": 11,
	"transformers_version": "4.29.2"
	}