solidrust
/

bagel-8b-v1.0-AWQ

Text Generation

4-bit precision

endpoints_compatible - llama-3 - bagel

text-generation-inference

Model card Files Files and versions

bagel-8b-v1.0-AWQ / quant_config.json

Ubuntu

adding quant config

2e36be3 over 1 year ago

history blame contribute delete

82 Bytes

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