mahihossain666
/

llama-2-70b-hf-quantized-3bits-GPTQ

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

Quantized to 3bit precision using AutoGPTQ.

Downloads last month: 47

Safetensors

Model size

7.54B params

Tensor type

I32

·

FP16

·

Dataset used to train mahihossain666/llama-2-70b-hf-quantized-3bits-GPTQ