🚀 Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

An open source implementation of CLIP.

A toolkit for efficiently fine-tuning LLM (InternLM, Llama, Baichuan, QWen, ChatGLM)

Best practice for training LLaMA models in Megatron-LM

MasaCtrl with T2I-Adapter for controllable consistent image synthesis and editing

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.

This is an official implementation for "Video Swin Transformers".