---
base_model: meta-llama/Llama-2-13b-hf
license: apache-2.0
inference: false
model_creator: Meta
model_name: Llama-2-13b-hf
quantized_by: Leliuga
pipeline_tag: text-generation
tags:
- llama-2
- arxiv:2307.09288
- arxiv:1910.09700
---
# Llama-2-13b-hf - bnb 4bit
- Model creator: [Meta](https://huggingface.co/meta-llama)
- Original model: [Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf)

## Description

This model is 4bit quantized version of [Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) using bitsandbytes. It's designed for fine-tuning! The PAD token is set as UNK.