-
Microsoft
- Tokyo, Japan
Stars
Bringing BERT into modernity via both architecture changes and scaling
📋 A list of open LLMs available for commercial use.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
The Official Python Client for Lamini's API
A machine learning project template that makes it easy to work with multiple Docker based VSCode Dev Containers. Easily transition projects to the cloud and production with automated code quality c…
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Dataframes powered by a multithreaded, vectorized query engine, written in Rust
Simple, safe way to store and distribute tensors
Convmelspec: Convertible Melspectrograms via 1D Convolutions
fsspec-compatible Azure Datake and Azure Blob Storage access
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
Hummingbird compiles trained ML models into tensor computation for faster inference.
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"
This repo hosts the code and models of "Masked Autoencoders that Listen".
A library for differentiable nonlinear optimization
Toolkit for creating, sharing and using natural language prompts.
PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)
TriMap: Large-scale Dimensionality Reduction Using Triplets
An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
Feathr – A scalable, unified data and AI engineering platform for enterprise
Code for Multiple Instance Active Learning for Object Detection, CVPR 2021
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
A lightweight library designed to accelerate the process of training PyTorch models by providing a minimal, but extensible training loop which is flexible enough to handle the majority of use cases…