In this article, we train the DistilGPT2 model for detective story generation. We use the Hugging Face Transformers library to fine-tune the model on Arthur Conan Doyle's collection of Sherlock Holmes stories. ...

In this article, we modify the FasterViT model for semantic segmentation model and carry out training on a leaf disease segmentation dataset. ...

In this article, we explore FasterViT for image classification which includes pretrained model image inference and fine-tuning the FasterViT model. ...

In this article, we go cover the Multiscale Vision Transformer model for video action recognition. ...

In this article, we try improving out face keypoint detection pipeline by using the YOLOV8 Nano model as the face detector and training a custom face keypoint regressor. ...