solidrust
/

Llama-3-16B-Instruct-v0.1-AWQ

Text Generation

4-bit precision

endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3

text-generation-inference

Model card Files Files and versions Community

Llama-3-16B-Instruct-v0.1-AWQ / quant_config.json

Ubuntu

adding quant config

50fc0d4 8 months ago

82 Bytes

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