Zero-Shot Image Classification
Transformers
ONNX
Chinese
English
m2_encoder
feature-extraction
multimodal
image-text-retrieval
bilingual
chinese
english
vision-language
custom-code
custom_code
Eval Results (legacy)
Instructions to use malusama/M2-Encoder-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use malusama/M2-Encoder-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="malusama/M2-Encoder-1B", trust_remote_code=True) pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("malusama/M2-Encoder-1B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| # code in this file is adpated from the ALBEF repo (https://github.com/salesforce/ALBEF) | |
| from torchvision import transforms | |
| from .randaugment import RandomAugment | |
| from PIL import Image | |
| def square_transform(size=224): | |
| return transforms.Compose( | |
| [ | |
| transforms.Resize((size, size), interpolation=Image.BICUBIC), | |
| transforms.ToTensor(), | |
| ] | |
| ) | |
| def square_transform_randaug(size=224): | |
| return transforms.Compose( | |
| [ | |
| transforms.RandomResizedCrop(size, scale=(0.8, 1.0), interpolation=Image.BICUBIC), | |
| transforms.RandomHorizontalFlip(), | |
| RandomAugment( | |
| 2, | |
| 7, | |
| isPIL=True, | |
| augs=[ | |
| "Identity", | |
| "AutoContrast", | |
| "Equalize", | |
| "Brightness", | |
| "Sharpness", | |
| "ShearX", | |
| "ShearY", | |
| "TranslateX", | |
| "TranslateY", | |
| "Rotate", | |
| ], | |
| ), | |
| transforms.ToTensor(), | |
| ] | |
| ) | |