MaziyarPanahi
/

Mistral-7B-Instruct-v0.2-AWQ

Text Generation

4-bit precision

arxiv:2310.06825

text-generation-inference

Model card Files Files and versions Community

Mistral-7B-Instruct-v0.2-AWQ / quant_config.json

MaziyarPanahi's picture

Upload folder using huggingface_hub

6c8c9f5 verified 4 months ago

raw history blame contribute delete

No virus

126 Bytes

	{
	"zero_point": true,
	"q_group_size": 128,
	"w_bit": 4,
	"version": "GEMM",
	"modules_to_not_convert": null
	}