README.md

---
license: other
tags:
- mlx
base_model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
---

# alexgusevski/Fallen-Llama-3.3-R1-70B-v1-Q8-mlx

The Model [alexgusevski/Fallen-Llama-3.3-R1-70B-v1-Q8-mlx](https://huggingface.co/alexgusevski/Fallen-Llama-3.3-R1-70B-v1-Q8-mlx) was converted to MLX format from [TheDrummer/Fallen-Llama-3.3-R1-70B-v1](https://huggingface.co/TheDrummer/Fallen-Llama-3.3-R1-70B-v1) using mlx-lm version **0.21.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/Fallen-Llama-3.3-R1-70B-v1-Q8-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)
```