Instructions to use mlx-community/siglip-so400m-patch14-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlx-community/siglip-so400m-patch14-224 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="mlx-community/siglip-so400m-patch14-224") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("mlx-community/siglip-so400m-patch14-224") model = AutoModelForZeroShotImageClassification.from_pretrained("mlx-community/siglip-so400m-patch14-224") - MLX
How to use mlx-community/siglip-so400m-patch14-224 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir siglip-so400m-patch14-224 mlx-community/siglip-so400m-patch14-224
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
mlx-community/siglip-so400m-patch14-224
The Model mlx-community/siglip-so400m-patch14-224 was converted to MLX format from google/siglip-so400m-patch14-224 using mlx-lm version 0.0.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/siglip-so400m-patch14-224")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 22
Hardware compatibility
Log In to add your hardware
Quantized