|
--- |
|
license: mit |
|
license_link: https://huggingface.co./microsoft/Phi-4-mini-instruct/resolve/main/LICENSE |
|
language: |
|
- multilingual |
|
pipeline_tag: text-generation |
|
tags: |
|
- nlp |
|
- code |
|
- mlx |
|
- mlx-my-repo |
|
widget: |
|
- messages: |
|
- role: user |
|
content: Can you provide ways to eat combinations of bananas and dragonfruits? |
|
library_name: transformers |
|
base_model: microsoft/Phi-4-mini-instruct |
|
--- |
|
|
|
# mlx-community/Phi-4-mini-instruct-8bit |
|
|
|
The Model [mlx-community/Phi-4-mini-instruct-8bit](https://huggingface.co./mlx-community/Phi-4-mini-instruct-8bit) was converted to MLX format from [microsoft/Phi-4-mini-instruct](https://huggingface.co./microsoft/Phi-4-mini-instruct) using mlx-lm version **0.21.5**. |
|
|
|
## Use with mlx |
|
|
|
```bash |
|
pip install mlx-lm |
|
``` |
|
|
|
```python |
|
from mlx_lm import load, generate |
|
|
|
model, tokenizer = load("mlx-community/Phi-4-mini-instruct-8bit") |
|
|
|
prompt="hello" |
|
|
|
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None: |
|
messages = [{"role": "user", "content": prompt}] |
|
prompt = tokenizer.apply_chat_template( |
|
messages, tokenize=False, add_generation_prompt=True |
|
) |
|
|
|
response = generate(model, tokenizer, prompt=prompt, verbose=True) |
|
``` |
|
|
