916 Open source projects that are alternatives of or similar to Cubert

LightSeq: A High Performance Inference Library for Sequence Processing and Generation

Explore the Capabilities of the TensorRT Platform

A library for high performance deep learning inference on NVIDIA GPUs.

TensorFlow examples in C, C++, Go and Python without bazel but with cmake and FindTensorFlow.cmake

Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

Running BERT without Padding

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

Source code that accompanies The CUDA Handbook.

NVIDIA-accelerated zero latency video compression library for interactive remoting applications

📘 A comprehensive handbook on how to create transformers for TypeScript with code examples

A C++-based, cross platform ray tracing library

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection, NeurIPS2020

A TensorFlow Implementation of the Transformer: Attention Is All You Need

cuDF - GPU DataFrame Library

Minimal runtime core of Caffe, Forward only, GPU support and Memory efficiency.

ArrayFire: a general purpose GPU library.

A python package to run contextualized topic modeling. CTMs combine BERT with topic models to get coherent topics. Also supports multilingual tasks. Cross-lingual Zero-shot model published at EACL 2021.

✍🏻 gpt2-client: Easy-to-use TensorFlow Wrapper for GPT-2 117M, 345M, 774M, and 1.5B Transformer Models 🤖 📝

GA-Net: Guided Aggregation Net for End-to-end Stereo Matching

A UNIVERSAL MUSIC TRANSLATION NETWORK - a method for translating music across musical instruments and styles.

Distribution-Aware Coordinate Representation for Human Pose Estimation

A single-header C++ library for simplifying the use of CUDA Runtime Compilation (NVRTC).

Sample codes for my CUDA programming book

Thin C++-flavored wrappers for the CUDA Runtime API

Snips NLU rust implementation

SIMD Library for Evaluating Elementary Functions, vectorized libm and DFT

CUDA programming in Julia.

PyTorch - Python + Nim

C++ library for solving large sparse linear systems with algebraic multigrid method

High-performance Bayesian Data Analysis on the GPU in Clojure

Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).

PageTransformer for flutter

Julia support for native CUDA programming

CUDA Data Parallel Primitives Library

VUDA is a header-only library based on Vulkan that provides a CUDA Runtime API interface for writing GPU-accelerated applications.

TypeScript transformer for improving the debugging experience of styled-components

Chinese version of GPT2 training code, using BERT tokenizer.

GPU-accelerated micromagnetic simulator

Stereo Semi Global Matching by cuda

A CUDA backend for Torch7

Simple implementations of NLP models. Tutorials are written in Chinese on my website https://mofanpy.com

TensorFlow implementation of 'Attention Is All You Need (2017. 6)'

A code generator for array-based code on CPUs and GPUs

The C++ parallel algorithms library.

BERT for Multitask Learning

Neural question generation using transformers

Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"

AI 尬舞机

Code for "Heterogeneous Graph Transformer" (WWW'20), which is based on pytorch_geometric

A TensorFlow-inspired neural network library built from scratch in C# 7.3 for .NET Standard 2.0, with GPU support through cuDNN

Implementation of SYCL for CPUs, AMD GPUs, NVIDIA GPUs

Abstractive summarisation using Bert as encoder and Transformer Decoder

A collection of GICP-based fast point cloud registration algorithms

Fast k nearest neighbor search using GPU

Python bindings for ArrayFire: A general purpose GPU library.

Laravel 5 JSON API Transformer Package

Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.

Implementation of State-of-the-art Text Classification Models in Pytorch

Run TensorFlow models in C++ without installation and without Bazel