🦜🔗 Build context-aware reasoning applications

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

Open-source implementation of Google Vizier for hyper parameters tuning

I have surveyed the technology and papers of CTR & Recommender System, and implemented 25 common-used models with Pytorch for reusage. （对工业界学术界的CTR推荐调研并实现25个算法模型，2023）