---
library_name: transformers
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
license: llama3.1
model-index:
- name: Meta-Llama-3.1-8B-Instruct-INT4
  results: []
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This is a quantized version of `Llama 3.1 70B Instruct`. Quantization to **4-bit** using `bistandbytes` and `accelerate`.

- **Developed by:** [More Information Needed]
- **License:** llama3.1
- **Base Model [optional]:** meta-llama/Meta-Llama-3.1-8B-Instruct

```python
# Use a pipeline as a high-level helper
from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="meta-llama/Meta-Llama-3.1-8B-Instruct")
pipe(messages)   Copy  # Load model directly
```

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
```

The model information can be found in the original [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)