| language: | |
| - en | |
| license: apache-2.0 | |
| tags: | |
| - mlx | |
| datasets: | |
| - cerebras/SlimPajama-627B | |
| - bigcode/starcoderdata | |
| - teknium/openhermes | |
| # mlx-community/TinyDolphin-2.8-1.1b-4bit-mlx | |
| This model was converted to MLX format from [`cognitivecomputations/TinyDolphin-2.8-1.1b`](). | |
| Refer to the [original model card](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b) 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/TinyDolphin-2.8-1.1b-4bit-mlx") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |