| language: | |
| - en | |
| license: apache-2.0 | |
| tags: | |
| - mlx | |
| datasets: | |
| - Skylion007/openwebtext | |
| - JeanKaddour/minipile | |
| pipeline_tag: text-generation | |
| inference: | |
| parameters: | |
| do_sample: true | |
| temperature: 0.5 | |
| top_p: 0.5 | |
| top_k: 50 | |
| max_new_tokens: 250 | |
| repetition_penalty: 1.176 | |
| # mlx-community/TinyMistral-248M-4bits | |
| The Model [mlx-community/TinyMistral-248M-4bits](https://huggingface.co/mlx-community/TinyMistral-248M-4bits) was converted to MLX format from [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M) using mlx-lm version **0.14.0**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("mlx-community/TinyMistral-248M-4bits") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |