MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
MIT License
An algorithm for cross-domain NL2SQL
TensorFlow 2 library implementing Graph Neural Networks
A flexible and efficient deep neural network (DNN) compiler that generates high-performance execu...
[CVPR 2023] Official Implementation of X-Decoder for generalized decoding for pixel, image and la...
Graphormer is a general-purpose deep learning backbone for molecular modeling.
Samples and Tools for Windows ML.
Foundation Architecture for (M)LLMs
Tutel MoE: An Optimized Mixture-of-Experts Implementation
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
CodeBERT
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using S...
Large-scale pretraining for dialogue
Hummingbird compiles trained ML models into tensor computation for faster inference.