| # Intelligent-Internet/II-Search-4B-MLX |
|
|
| This model [Intelligent-Internet/II-Search-4B-MLX ](https://huggingface.co/Intelligent-Internet/II-Search-4B-MLX) was |
| converted to MLX format from [Intelligent-Internet/II-Search-4B](https://huggingface.co/Intelligent-Internet/II-Search-4B) |
| using mlx-lm version **0.26.1**. |
|
|
| ## Use with mlx |
|
|
| ```bash |
| pip install mlx-lm |
| ``` |
|
|
| ```python |
| from mlx_lm import load, generate |
| |
| model, tokenizer = load("Intelligent-Internet/II-Search-4B-MLX") |
| |
| prompt = "hello" |
| |
| if tokenizer.chat_template is not None: |
| messages = [{"role": "user", "content": prompt}] |
| prompt = tokenizer.apply_chat_template( |
| messages, add_generation_prompt=True |
| ) |
| |
| response = generate(model, tokenizer, prompt=prompt, verbose=True) |
| ``` |
|
|
| ## Important: Integrate web_search and web_visit tools |
|
|
| Equip the served model with web_search and web_visit tools to enable internet-aware functionality. Alternatively, use a middleware like MCP for tool integration—see this example repository: https://github.com/hoanganhpham1006/mcp-server-template. |
