metadata
license: mit
LCL-ViT-B/16_Laion
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.
license: mit
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.