Model Card for CLIP ViT B/32 roberta base LAION 2B Table of Contents 1. Model Details 2. Uses 3. Training Details 4. Evaluation 5. Acknowledgements 6. Citation 7. How To Get Started With the Model Model Details Model Description A CLIP ViT B/32 roberta base model trained with the LAION 2B English subset of LAION 5B (https://laion.ai/blog/laion 5b/) using OpenCLIP (https://github.com/mlfoundations/open clip). Model training done by Romain Beaumont on the stability.ai cluster. Uses Direct Use Zero shot image classification, image and text retrieval, among others. Downstream Use Image classification and other image task fine tuning, linear probe image classification, image generation guiding and conditioning, among others. Training Details Training Data This model was trained with the 2 Billion sample English subset of LAION 5B (https://laion.ai/blog/laion 5b/). Training Procedure Training with batch size 32k for 12B sample of laion2B en, see https://wandb.ai/rom1504/open clip/reports/clip B 32 roberta base VmlldzoyOTM0NDQ3 Model is B/32 on visual side, roberta base initialized with pretrained weights on text side. Evaluation Evaluation done with code in the LAION CLIP Benchmark suite…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy