TheBloke
/

Mixtral_34Bx2_MoE_60B-AWQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Mixtral_34Bx2_MoE_60B-AWQ / quant_config.json

TheBloke's picture

AWQ model commit

1662a77 7 months ago

history blame contribute delete

No virus

144 Bytes

	{
	"zero_point": true,
	"q_group_size": 128,
	"w_bit": 4,
	"version": "GEMM",
	"modules_to_not_convert": [
	"gate"
	]
	}