| This model was exported using [GPTQModel](https://github.com/ModelCloud/GPTQModel). Below is example code for exporting a model from GPTQ format to MLX format. | |
| ## Example: | |
| ```python | |
| from gptqmodel import GPTQModel | |
| # load gptq quantized model | |
| gptq_model_path = "ModelCloud/Falcon3-10B-Instruct-gptqmodel-4bit-vortex-v1" | |
| mlx_path = f"./vortex/Falcon3-10B-Instruct-gptqmodel-4bit-vortex-v1-mlx" | |
| # export to mlx model | |
| GPTQModel.export(gptq_model_path, mlx_path, "mlx") | |
| # load mlx model check if it works | |
| from mlx_lm import load, generate | |
| mlx_model, tokenizer = load(mlx_path) | |
| prompt = "The capital of France is" | |
| messages = [{"role": "user", "content": prompt}] | |
| prompt = tokenizer.apply_chat_template( | |
| messages, add_generation_prompt=True | |
| ) | |
| text = generate(mlx_model, tokenizer, prompt=prompt, verbose=True) | |
| ``` |