language: | |
- multilingual | |
license: mit | |
tags: | |
- nlp | |
- code | |
- mlx | |
license_link: https://huggingface.co/microsoft/Phi-3-small-8k-instruct/resolve/main/LICENSE | |
pipeline_tag: text-generation | |
inference: | |
parameters: | |
temperature: 0.7 | |
widget: | |
- messages: | |
- role: user | |
content: Can you provide ways to eat combinations of bananas and dragonfruits? | |
# mlx-community/Phi-3-small-8k-instruct-AQ4_32 | |
The Model [mlx-community/Phi-3-small-8k-instruct-AQ4_32](https://huggingface.co/mlx-community/Phi-3-small-8k-instruct-AQ4_32) was converted to MLX format from [microsoft/Phi-3-small-8k-instruct](https://huggingface.co/microsoft/Phi-3-small-8k-instruct) using mlx-lm version **0.14.1**. | |
## Use with mlx | |
```bash | |
pip install mlx-lm | |
``` | |
```python | |
from mlx_lm import load, generate | |
model, tokenizer = load("mlx-community/Phi-3-small-8k-instruct-AQ4_32") | |
response = generate(model, tokenizer, prompt="hello", verbose=True) | |
``` | |