Image Feature Extraction
Transformers
JAX
Safetensors
MLX
PyTorch
aimv2_vision_model
vision
custom_code
Eval Results (legacy)
Instructions to use apple/aimv2-1B-patch14-448 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apple/aimv2-1B-patch14-448 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="apple/aimv2-1B-patch14-448", trust_remote_code=True)# Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("apple/aimv2-1B-patch14-448", trust_remote_code=True) model = AutoModel.from_pretrained("apple/aimv2-1B-patch14-448", trust_remote_code=True) - MLX
How to use apple/aimv2-1B-patch14-448 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir aimv2-1B-patch14-448 apple/aimv2-1B-patch14-448
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- Xet hash:
- 71724cc835744989001eceb3ca067eefcdce58d25fb0d8c7c4b9eeb36483f6d7
- Size of remote file:
- 4.95 GB
- SHA256:
- 902ccd46e2c5be017633e9aad00889122207c0404b5d4267432988ad4eba3a56
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.