solidrust
/

dolphin-2.8-mistral-7b-v02-AWQ-gemv-64gs

Text Generation

Generated from Trainer

4-bit precision

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

dolphin-2.8-mistral-7b-v02-AWQ-gemv-64gs / quant_config.json

Shaun Prince

adding AWQ model

d614f18 7 months ago

history blame contribute delete

82 Bytes

	{
	"zero_point": true,
	"q_group_size": 64,
	"w_bit": 4,
	"version": "GEMV"
	}