This package provides an implementation of today’s most used tokenizers, with a focus on performance and versatility.

ggml is a ML library written in C and C++ with a focus on transformer inference, similar to ML libraries such as PyTorch and TensorFlow.

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

Inquirer should ease the process of asking end user questions, parsing, validating answers, managing hierarchical prompts and providing error feedback.

TensorFlow is a flexible platform for building and training machine learning models. This package provides the "lite" variant for mobile devices.

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.

This is a small self-contained low-precision general matrix multiplication (GEMM) library. It is not a full linear algebra library. Low-precision means that the input and output matrix entries are integers on at most 8 bits. To avoid overflow, results are internally accumulated on more than 8 bits, and at the end only some significant 8 bits are kept.

This package includes a variety of tools used to analyze persistence diagrams. It currently houses implementations of

• Persistence images

• Persistence landscapes

• Bottleneck distance

• Modified Gromov–Hausdorff distance

• Sliced Wasserstein kernel

• Heat kernel

• Diagram plotting

This package provides a standard API for reinforcement learning and a diverse set of reference environments (formerly Gym).

Hmmlearn is a set of algorithms for unsupervised learning and inference of Hidden Markov Models.

This package provides provides an implementation of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for Python.

DMLC-Core is the backbone library to support all DMLC projects, offers the bricks to build efficient and scalable distributed machine learning libraries.

This package provides a Python implementation of the CMA-ES algorithm and a few related numerical optimization tools.

Argos Translate uses OpenNMT for translations and can be used as either a Python library, command-line, or GUI application. It supports installing language model packages which are ZIP archives with a .argosmodel extension. This package provides a Qt interface for Argos Translate.

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.

Pomegranate is a graphical models library for Python, implemented in Cython for speed.

This package provides a speech recognition toolkit based on kaldi. It supports more than 20 languages and dialects - English, Indian English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino, Ukrainian, Kazakh, Swedish, Japanese, Esperanto, Hindi, Czech, Polish. The program works offline, even on lightweight devices. Portable per-language models are about 50Mb each, and there are much bigger and precise models available.

Vosk API provides a streaming API allowing to use it on-the-fly and bindings for different programming languages. It allows quick reconfiguration of vocabulary for better accuracy, and supports speaker identification beside simple speech recognition.

This package provides a speech recognition toolkit based on kaldi. It supports more than 20 languages and dialects - English, Indian English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino, Ukrainian, Kazakh, Swedish, Japanese, Esperanto, Hindi, Czech, Polish. The program works offline, even on lightweight devices. Portable per-language models are about 50Mb each, and there are much bigger and precise models available.

Vosk API provides a streaming API allowing to use it on-the-fly and bindings for different programming languages. It allows quick reconfiguration of vocabulary for better accuracy, and supports speaker identification beside simple speech recognition.

This package provides a C++ and Python library for performing arbitrary optimizations on ONNX models, as well as a growing list of prepackaged optimization passes.

Not all possible optimizations can be directly implemented on ONNX graphs--- some will need additional backend-specific information---but many can, and the aim is to provide all such passes along with ONNX so that they can be re-used with a single function call.

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

Apache Burr makes it easy to develop applications that make decisions (chatbots, agents, simulations, etc...) from simple Python building blocks. Apache Burr works well for any application that uses LLMs, and can integrate with any of your favorite frameworks. Burr includes a UI that can track/monitor/trace your system in real time, along with pluggable persisters (e.g. for memory) to save and load application state.

This package is a stand-alone implementation of several NumPy dtype extensions used in machine learning libraries, including:

• bfloat16: an alternative to the standard float16 format

• float8_*: several experimental 8-bit floating point representations including:

  • float8_e4m3b11fnuz

  • float8_e4m3fn

  • float8_e4m3fnuz

  • float8_e5m2

  • float8_e5m2fnuz

• int4 and uint4: low precision integer types.

The GeomLoss library provides efficient GPU implementations for:

• Kernel norms (also known as Maximum Mean Discrepancies).

• Hausdorff divergences, which are positive definite generalizations of the Chamfer-ICP loss and are analogous to log-likelihoods of Gaussian Mixture Models.

• Debiased Sinkhorn divergences, which are affordable yet positive and definite approximations of Optimal Transport (Wasserstein) distances.

This package provides a tool for visualizing live, rich data for Torch and Numpy.