nicholasKluge
/

TeenyTinyLlama-460m-awq

Text Generation

text-generation-inference

Carbon Emissions

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

TeenyTinyLlama-460m-awq / quant_config.json

nicholasKluge's picture

Upload folder using huggingface_hub

e522bd1 verified 5 months ago

raw history blame contribute delete

No virus

90 Bytes

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