SamMikaelson
/

deepseek-ocr-gptq-4bit

4-bit precision

Model card Files Files and versions

deepseek-ocr-gptq-4bit / generation_config.json

SamMikaelson's picture

Upload GPTQ 4-bit packed model (75.0% size reduction, 4.0x compression)

42a1727 verified 8 days ago

history blame contribute delete

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 0,
	"eos_token_id": 1,
	"transformers_version": "4.46.3"
	}