TheBloke
/

Falcon-180B-Chat-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Falcon-180B-Chat-GPTQ / generation_config.json

TheBloke's picture

Add sharded 4-bit GPTQ in place of split files

89eabf0 about 1 year ago

113 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 11,
	"eos_token_id": 11,
	"transformers_version": "4.33.0"
	}