---
license: apache-2.0
language:
- en
base_model: watt-ai/watt-tool-70B
tags:
- function-calling
- tool-use
- llama
- bfcl
- mlx
- mlx-my-repo
---

# hellosri/watt-tool-70B-mlx-8Bit

The Model [hellosri/watt-tool-70B-mlx-8Bit](https://huggingface.co/hellosri/watt-tool-70B-mlx-8Bit) was converted to MLX format from [watt-ai/watt-tool-70B](https://huggingface.co/watt-ai/watt-tool-70B) using mlx-lm version **0.22.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("hellosri/watt-tool-70B-mlx-8Bit")

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)
```