| license: apache-2.0 | |
| tags: | |
| - trl | |
| - orpo | |
| - generated_from_trainer | |
| - mlx | |
| base_model: mistral-community/Mixtral-8x22B-v0.1 | |
| datasets: | |
| - argilla/distilabel-capybara-dpo-7k-binarized | |
| inference: | |
| parameters: | |
| temperature: 0.7 | |
| model-index: | |
| - name: zephyr-orpo-141b-A35b-v0.1 | |
| results: [] | |
| # mlx-community/zephyr-orpo-141b-A35b-v0.1-8bit | |
| This model was converted to MLX format from [`HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1`]() using mlx-lm version **0.9.0**. | |
| Refer to the [original model card](https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1) for more details on the model. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("mlx-community/zephyr-orpo-141b-A35b-v0.1-8bit") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |