| license: other | |
| tags: | |
| - generated_from_trainer | |
| - mlx | |
| base_model: Qwen/Qwen2-beta-4B | |
| model-index: | |
| - name: quyen-4b | |
| results: [] | |
| # vilm/Quyen-mlx | |
| This model was converted to MLX format from [`vilm/Quyen-4e`](). | |
| Refer to the [original model card](https://huggingface.co/vilm/Quyen-4e) for more details on the model. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("vilm/Quyen-mlx") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |