Instructions to use mlx-community/phi-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/phi-2 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/phi-2") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- MLX LM
How to use mlx-community/phi-2 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "mlx-community/phi-2" --prompt "Once upon a time"
Remove ln to weights in snippet
Browse files
README.md
CHANGED
|
@@ -30,9 +30,6 @@ git clone https://github.com/ml-explore/mlx-examples.git
|
|
| 30 |
export HF_HUB_ENABLE_HF_TRANSFER=1
|
| 31 |
huggingface-cli download --local-dir-use-symlinks False --local-dir phi-2 mlx-community/phi-2
|
| 32 |
|
| 33 |
-
# The phi2 example script currently requires the weights to be in the current dir
|
| 34 |
-
ln -s phi-2/weights.npz .
|
| 35 |
-
|
| 36 |
# Run example
|
| 37 |
python mlx-examples/phi2/phi2.py --prompt "My name is"
|
| 38 |
```
|
|
|
|
| 30 |
export HF_HUB_ENABLE_HF_TRANSFER=1
|
| 31 |
huggingface-cli download --local-dir-use-symlinks False --local-dir phi-2 mlx-community/phi-2
|
| 32 |
|
|
|
|
|
|
|
|
|
|
| 33 |
# Run example
|
| 34 |
python mlx-examples/phi2/phi2.py --prompt "My name is"
|
| 35 |
```
|