OpenGVLab
/

LCL-ViT-B-16-Laion

Model card Files Files and versions

LCL-ViT-B/16_Laion

[📜 Paper] [📂 GitHub]

This is the model of the paper Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning.

Please refer to https://github.com/OpenGVLab/LCL for details.

Downloads last month: 29

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for OpenGVLab/LCL-ViT-B-16-Laion

Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning

Paper • 2406.07543 • Published Jun 11, 2024