solidrust
/

Neural-Story-7B-instruct-v0.2-AWQ

Text Generation

4-bit precision

Inference Endpoints

text-generation-inference

Generated from Trainer

Model card Files Files and versions Community

Neural-Story-7B-instruct-v0.2-AWQ / quant_config.json

Suparious's picture

Create quant_config.json

4adf249 verified 12 months ago

history blame contribute delete

90 Bytes

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