Repo for WWW 2022 paper: Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval
MIT License
Generation of protein sequences and evolutionary alignments via discrete diffusion models
Secure AI Solutions
Subseasonal forecasting models
To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention,...
Building modular LMs with parameter-efficient fine-tuning.
Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documen...
An end-to-end sample of RAG showcasing development, evaluation, experimentation, and deployment u...
A Python package for generating concise, high-quality summaries of a probability distribution
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Community for applying LLMs to robotics and a robot simulator with ChatGPT integration
Tutel MoE: An Optimized Mixture-of-Experts Implementation