TheBloke
/

deepseek-llm-67b-chat-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

deepseek-llm-67b-chat-GPTQ / quantize_config.json

TheBloke's picture

GPTQ model commit

d7cd6c8 6 months ago

raw history blame

185 Bytes

	{
	"bits": 3,
	"group_size": 32,
	"damp_percent": 0.1,
	"desc_act": true,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": "model"
	}