Modelpublic

Advantech-EIOT/intel_llama-3.1-8b-instruct

sourceHugging Facellama3.1updated 2y agoView on Hugging Face

0likes7downloads

Model Card

model_name: Llama 3.1 8B Instruct

arxiv: 2204.05149

base_model: meta-llama/Llama-3.1-8B-Instruct

model_creator: Meta Llama 3.1

model_type: llama

pipeline_tag: text-generation

modeltransformationon: Ubuntu 24.04 / OpenVINO 2024.3.0

quantized_by: OpenVINO models using NNCF to int4

Llama 3.1 8B Instruct - IR

—Model creator: Meta Llama 3.1
—Original model: Llama-3.1-8B-Instruct