---
language:
- en
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
license: llama2
---

# Model Card for LlamaGuard-7b-GGUF

This is a quantized model for `meta-llama/LlamaGuard-7b`. Two quantization methods were used:
- Q5_K_M: 5-bit, preserves most of the model's performance
- Q4_K_M: 4-bit, smaller footprints and saves more memory

## Model Details

### Model Description

Refer to details from [Meta's official model card]: (https://huggingface.co/meta-llama/LlamaGuard-7b).