solidrust
/

mistral-7b-v0.2-layla-v4-AWQ

Text Generation

Inference Endpoints

4-bit precision

text-generation-inference

Model card Files Files and versions Community

mistral-7b-v0.2-layla-v4-AWQ / quant_config.json

Shaun Prince

adding quant config

6312ef3 4 months ago

No virus

82 Bytes

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