solidrust
/

Memgpt-3x7b-MOE-AWQ

Text Generation

4-bit precision

Inference Endpoints

Mixture of Experts

starsnatched/MemGPT-DPO

starsnatched/MemGPT-3

starsnatched/MemGPT

text-generation-inference

Model card Files Files and versions Community

Memgpt-3x7b-MOE-AWQ / quant_config.json

Ubuntu

adding quant config

b10aa30 8 months ago

82 Bytes

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