| language: | |
| - en | |
| license: apache-2.0 | |
| tags: | |
| - mlx | |
| datasets: | |
| - cognitivecomputations/dolphin | |
| - jondurbin/airoboros-2.2.1 | |
| - cognitivecomputations/dolphin-coder | |
| - teknium/openhermes | |
| - ise-uiuc/Magicoder-OSS-Instruct-75K | |
| - ise-uiuc/Magicoder-Evol-Instruct-110K | |
| - LDJnr/Capybara | |
| # mlx-community/dolphin-2.7-mixtral-8x7b | |
| This model was converted to MLX format from [`cognitivecomputations/dolphin-2.7-mixtral-8x7b`]() using mlx-lm version **0.7.0**. | |
| Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.7-mixtral-8x7b) 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/dolphin-2.7-mixtral-8x7b") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |