---
license: llama3.1
language:
- en
pipeline_tag: text-generation
datasets:
- allenai/llama-3.1-tulu-3-70B-preference-mixture
base_model: allenai/Llama-3.1-Tulu-3-70B-DPO
library_name: transformers
tags:
- mlx
---

# Scotto2025/Llama-3.1-Tulu-3-70B-DPO-Q4-mlx

The Model [Scotto2025/Llama-3.1-Tulu-3-70B-DPO-Q4-mlx](https://huggingface.co/Scotto2025/Llama-3.1-Tulu-3-70B-DPO-Q4-mlx) was converted to MLX format from [allenai/Llama-3.1-Tulu-3-70B-DPO](https://huggingface.co/allenai/Llama-3.1-Tulu-3-70B-DPO) using mlx-lm version **0.20.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Scotto2025/Llama-3.1-Tulu-3-70B-DPO-Q4-mlx")

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)
```