CTranslate2 is a C++ and Python library for efficient inference with Transformer models.

The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.

SentencePiece is an unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabulary size is predetermined prior to the neural model training. SentencePiece implements subword units---e.g., byte-pair-encoding (BPE) and unigram language model---with the extension of direct training from raw sentences. SentencePiece allows us to make a purely end-to-end system that does not depend on language-specific pre- or post-processing.

DeepXDE is a library for scientific machine learning and physics-informed learning. It includes implementations for the PINN (physics-informed neural networks), DeepONet (deep operator network) and MFNN (multifidelity neural network) algorithms.

This package provides a tensor-like library for functions and distributions.

MNN is a deep learning framework. It supports inference and training of deep learning models for inference and training on-device.

ONNX Runtime is a performance-focused complete scoring engine for Open Neural Network Exchange (ONNX) models, with an open extensible architecture to continually address the latest developments in AI and Deep Learning. ONNX Runtime stays up to date with the ONNX standard with complete implementation of all ONNX operators, and supports all ONNX releases (1.2+) with both future and backwards compatibility.

This package provides easy download of thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio.

These models can be applied on:

• Text, for tasks like text classification, information extraction, question answering, summarization, translation, and text generation, in over 100 languages.

• Images, for tasks like image classification, object detection, and segmentation.

• Audio, for tasks like speech recognition and audio classification.

Transformer models can also perform tasks on several modalities combined, such as table question answering, optical character recognition, information extraction from scanned documents, video classification, and visual question answering.

This package provides APIs to quickly download and use those pretrained models on a given text, fine-tune them on your own datasets and then share them with the community. At the same time, each Python module defining an architecture is fully standalone and can be modified to enable quick research experiments.

Transformers is backed by the three most popular deep learning libraries — Jax, PyTorch and TensorFlow — with a seamless integration between them.

This package provides fast machine learning algorithms including matrix factorization and divisive clustering for large sparse and dense matrices.

This tool provides ordinary differential equation solvers implemented in PyTorch. Backpropagation through ODE solutions is supported using the adjoint method for constant memory cost.

Random Jungle is an implementation of Random Forests. It is supposed to analyse high dimensional data. In genetics, it can be used for analysing big Genome Wide Association (GWA) data. Random Forests is a powerful machine learning method. Most interesting features are variable selection, missing value imputation, classifier creation, generalization error estimation and sample proximities between pairs of cases.

xx_sent_ud_sm is a spaCy model optimized for CPU. It includes a sentence boundary component of a relatively small size.

ONNX is a format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types.

Low-precision, high-performance matrix-matrix multiplications and convolution library for server-side inference.

This Python library provides several solvers for optimization problems related to Optimal Transport for signal, image processing and machine learning.

Thread-pool Controls provides Python helpers to limit the number of threads used in the threadpool-backed of common native libraries used for scientific computing and data science (e.g. BLAS and OpenMP).

Autograd can automatically differentiate native Python and NumPy code. It can handle a large subset of Python's features, including loops, ifs, recursion and closures, and it can even take derivatives of derivatives of derivatives. It supports reverse-mode differentiation (a.k.a. backpropagation), which means it can efficiently take gradients of scalar-valued functions with respect to array-valued arguments, as well as forward-mode differentiation, and the two can be composed arbitrarily. The main intended application of Autograd is gradient-based optimization.

OpenFst is a library for constructing, combining, optimizing, and searching weighted finite-state transducers (FSTs).

This is a real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framework and implemented in Python.

This package provides a port to Facebook's LLaMA collection of foundation language models. It requires models parameters to be downloaded independently to be able to run a LLaMA model.

This package provides a generic API for dispatch to Pyro backends.

This package implements the Hopcroft-Karp algorithm, producing a maximum cardinality matching from a bipartite graph.

This package implements a variety of persistent homology algorithms. It provides an interface for

• computing persistence cohomology of sparse and dense data sets

• visualizing persistence diagrams

• computing lowerstar filtrations on images

• computing representative cochains

This framework provides an easy method to compute dense vector representations for sentences, paragraphs, and images. The models are based on transformer networks like BERT / RoBERTa / XLM-RoBERTa and achieve state-of-the-art performance in various tasks. Text is embedded in vector space such that similar text are closer and can efficiently be found using cosine similarity.

This package provides easy access to pretrained models for more than 100 languages, fine-tuned for various use-cases.

Further, this framework allows an easy fine-tuning of custom embeddings models, to achieve maximal performance on your specific task.

Scikit-learn provides simple and efficient tools for data mining and data analysis.