TheBloke
/

Mistral-7B-Claude-Chat-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Mistral-7B-Claude-Chat-GPTQ / quantize_config.json

TheBloke's picture

GPTQ model commit

5d9f327 7 months ago

raw history blame

No virus

134 Bytes

	{
	"bits": 8,
	"group_size": 128,
	"damp_percent": 0.01,
	"desc_act": true,
	"sym": true,
	"true_sequential": true
	}