Instructions to use openai/clip-vit-base-patch32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/clip-vit-base-patch32 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="openai/clip-vit-base-patch32") 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, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32") model = AutoModelForZeroShotImageClassification.from_pretrained("openai/clip-vit-base-patch32", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Subject: Commercial Use and Licensing Clarification for CLIP ViT-B/32 ONNX Conversion
#75
by bazzopk - opened
Hello OpenAI Team,
We are developing BAZZO, a commercial e-commerce marketplace, and plan to use openai/clip-vit-base-patch32 for image similarity search.
The ONNX Community maintainer has confirmed that onnx-community/clip-vit-base-patch32-ONNX was converted directly from the original OpenAI model without modifying the pretrained weights.
Before deploying it in production, we would appreciate clarification on the following:
- Can the original pretrained CLIP ViT-B/32 weights and their ONNX conversion be used commercially in an e-commerce application?
- Does the MIT license cover the pretrained model weights as well as the source code?
- Which copyright, license, and attribution notices must we preserve?
- Are there any additional licensing restrictions or requirements for commercial production deployment?
We would appreciate an official licensing reference or confirmation.
Thank you.
BAZZO Team