README.md

---
base_model: gradientai/Llama-3-8B-Instruct-Gradient-4194k
language:
- en
license: llama3
pipeline_tag: text-generation
tags:
- meta
- llama-3
- mlx
---

# mlx-community/gradientai_Llama-3-8B-Instruct-Gradient-4194k_4bit

The Model [mlx-community/gradientai_Llama-3-8B-Instruct-Gradient-4194k_4bit](https://huggingface.co/mlx-community/gradientai_Llama-3-8B-Instruct-Gradient-4194k_4bit) was converted to MLX format from [gradientai/Llama-3-8B-Instruct-Gradient-4194k](https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-4194k) using mlx-lm version **0.19.3**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gradientai_Llama-3-8B-Instruct-Gradient-4194k_4bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```