Zero-Shot Image Classification
Transformers
Safetensors
tipsv2
feature-extraction
vision
image-text
contrastive-learning
zero-shot
custom_code
Instructions to use google/tipsv2-so400m14 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/tipsv2-so400m14 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="google/tipsv2-so400m14", trust_remote_code=True) pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("google/tipsv2-so400m14", trust_remote_code=True) model = AutoModel.from_pretrained("google/tipsv2-so400m14", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update configuration_tips.py
Verified signatureUploads configuration_tips.py.b8b7ff5 -
Update files for transformers integration
Verified signatureUpdates the repo to smoothly integrate with transformers. PR: https://github.com/huggingface/transformers/pull/46347 Changes: - Update `config.json` to match transformers structure - Update config classes to handle new `config.json` - Add processor and tokenizer configs - Update DPT `model.safetensors` files to include DPT head + backbone weights - Update DPT model code to handle extra weights in `model.safetensors` fileb160241
-
Fix broken image URL and add missing .cpu() in code snippets
Verified signature44ff952 -
Remove zero-shot segmentation snippet, link to GitHub for advanced use cases
Gabriele6b864bd
-
PCA visualization: add whitening and sigmoid
Gabriele190b924 -
Add navigation table linking all variants and DPT heads
Gabriele54de1d9
-
Switch to bus image with matching classes
Gabriele3df09f9 -
Improve code examples: better classes, descriptive comments
Gabriele828f85a -
Use cat photo, add print statements to code examples
Gabriele4407365 -
Fix meta device crash: use pure Python for drop_path_rate
Gabriele05bf02c -
Fix zero-shot segmentation section, use public example image
Gabriele2bad776
-
Update README
Gabriele3d0bb08 -
Align image_encoder.py drop_path_rate computation with upstream
Gabriele99e5c3a -
Upload README.md with huggingface_hub
Verified signaturea850c10
-
Upload model.safetensors with huggingface_hub
Verified signature3d18392 -
Upload README.md with huggingface_hub
Verified signature7b64de5 -
Upload config.json with huggingface_hub
Verified signature3604628 -
Upload tokenizer.model with huggingface_hub
Verified signature54a858f -
Upload text_encoder.py with huggingface_hub
Verified signature1eed93f -
Upload image_encoder.py with huggingface_hub
Verified signaturebeee260 -
Upload modeling_tips.py with huggingface_hub
Verified signature3fef103 -
Upload configuration_tips.py with huggingface_hub
Verified signature96352c1 -
initial commit
Verified signatured94c78b