---
base_model: meta-llama/Meta-Llama-3-8B-Instruct
license: other
license_name: llama3
license_link: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/raw/main/LICENSE
inference: false
model_creator: Meta
model_name: Meta-Llama-3-8B-Instruct
quantized_by: Leliuga
pipeline_tag: text-generation
tags:
- llama
- llama-3
---
# Meta-Llama-3-8B-Instruct - bnb 4bit
- Model creator: [Meta](https://huggingface.co/meta-llama)
- Original model: [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)

## Description

This model is 4bit quantized version of [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) using bitsandbytes. It's designed for fine-tuning! The PAD token is set as UNK.