Model Selection

Trained on 1.4B data

# Trained on 1.4B data

CLIP ViT B 32 256x256 DataComp S34b B86k

This is a CLIP ViT-B/32 model trained on the DataComp-1B dataset using the OpenCLIP framework at 256x256 resolution, primarily for zero-shot image classification and image-text retrieval tasks.

Featured Recommended AI Models

AIbase

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

© 2025AIbase