heyholetsgo
/

Nous-Hermes-2-Mistral-7B-DPO-AWQ

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Nous-Hermes-2-Mistral-7B-DPO-AWQ / quant_config.json

heyholetsgo's picture

Add missing quant_config.json for compatibility with vLLM backends out of the box. (#1)

ba126fb verified 8 months ago

history blame contribute delete

90 Bytes

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