Qualcomm® AI HubAI Hub

OpenAI-Clip

Multi-modal foundational model for vision and language tasks like image/text similarity and for zero-shot image classification.

Contrastive Language-Image Pre-Training (CLIP) uses a ViT like transformer to get visual features and a causal language model to get the text features. Both the text and visual features can then be used for a variety of zero-shot learning tasks.

Snapdragon® X Elite
8.43ms
Inference Time
0MB
Memory Usage
377NPU
Layers

Technical Details

Model checkpoint:ViT-B/16
Image input resolution:224x224
Text context length:77
Number of parameters (CLIPTextEncoder):76.0M
Model size (CLIPTextEncoder):290 MB
Number of parameters (CLIPImageEncoder):115M
Model size (CLIPImageEncoder):437 MB

Applicable Scenarios

  • Image Search
  • Content Moderation
  • Caption Creation

Licenses

Source Model:MIT
Deployable Model:AI Model Hub License

Tags

  • foundation
    A “foundation” model is versatile and designed for multi-task capabilities, without the need for fine-tuning.

Supported Compute Chipsets

  • Snapdragon® X Elite