-
Microsoft
- Redmond
- https://www.microsoft.com/en-us/research/people/youki/
Stars
FastFormers - highly efficient transformer models for NLU
Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
Transformer based on a variant of attention that is linear complexity in respect to sequence length
My take on a practical implementation of Linformer for Pytorch.
Repository for the paper "Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning"
W4ngatang / transformers
Forked from huggingface/transformers🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
int8_t and int16_t matrix multiply based on https://arxiv.org/abs/1705.01991
marian-nmt / FBGEMM
Forked from pytorch/FBGEMMFB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
Fast Neural Machine Translation in C++ - development repository
FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Create and modify Word documents with Python
Sarasra / models
Forked from tensorflow/modelsModels and examples built with TensorFlow
oneAPI Deep Neural Network Library (oneDNN)
Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Implementing Recurrent Neural Network from Scratch