Taskres and CoOp prompts for CLIP - ViT-B/16, RN50, RN101, ViT-L/14, ViT-B/32

The tuned prompts for CLIP using Taskres (Yu, T., Lu, Z., Jin, X., Chen, Z., & Wang, X. (2023). Task residual for tuning vision-language models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition) and CoOp (Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022). Learning to prompt for vision-language models. International Journal of Computer Vision, 130(9)).
Used in TransCLIP (Zanella, M., Gérin, B., & Ayed, I. (2024). Boosting vision-language models with transduction. Advances in Neural Information Processing Systems, 37, 62223-62256.) and OGA (Fuchs, C., Zanella, M., & De Vleeschouwer, C. (2025). Online Gaussian Test-Time Adaptation of Vision-Language Models. In CVPR Workshops - 8th Multimodal Learning and Applications workshop 2025).