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 Settings
- 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"
- Atomic Chat
Update README.md to download the model at the right location
Browse filesthis downloads the model at the right location to be used as prescribed in the example.
README.md
CHANGED
|
@@ -30,7 +30,7 @@ cd mlx-examples
|
|
| 30 |
|
| 31 |
# Download model
|
| 32 |
export HF_HUB_ENABLE_HF_TRANSFER=1
|
| 33 |
-
huggingface-cli download --local-dir-use-symlinks False --local-dir
|
| 34 |
|
| 35 |
# Run example
|
| 36 |
python llms/phi2/phi2.py --prompt "My name is"
|
|
|
|
| 30 |
|
| 31 |
# Download model
|
| 32 |
export HF_HUB_ENABLE_HF_TRANSFER=1
|
| 33 |
+
huggingface-cli download --local-dir-use-symlinks False --local-dir llms/phi2 mlx-community/phi-2
|
| 34 |
|
| 35 |
# Run example
|
| 36 |
python llms/phi2/phi2.py --prompt "My name is"
|