Directory
Published directory entries matching your search.
NMF.jl is a Julia package for non-negative matrix factorization, which factorizes a non-negative matrix into two lower-rank non-negative matrices. The nnmf function runs initialization and optimization in one call. Implemented methods include multiplicative update, projected alternating least squares, projected gradient and coordinate descent, with random and NNDSVD initialization.
nn_builder is a tool for building neural networks with less boilerplate code; the user specifies the network type and it builds it. It supports NN, CNN and RNN networks for PyTorch and TensorFlow 2.0, taking arguments such as layers_info, hidden_activations and dropout.
nnx is an open source GitHub repository that acts as an extension to Torch7's nn neural network package. It provides additional experimental components for use with the Torch7 nn library.
Nos is an open-source module for running AI workloads on Kubernetes, intended to increase GPU utilization, cut infrastructure costs and improve workload performance. It provides dynamic GPU partitioning and elastic resource quota management.
Numla is a minimal browser-based calculator notepad for quick everyday calculations, including arithmetic, currency conversions, percentages, and unit conversions. It operates entirely locally with no user accounts or tracking, supports offline use, and includes features such as tabbed notes, instant note search, a Time Machine version history tool, focus mode, theme customization, and .txt file export. It is distributed as a progressive web app.
NuriStat is a free open-source alternative to SPSS, a menu-driven statistics tool designed for researchers and clinicians. It provides 27 or more analysis modules, variable metadata support, SPSS import functionality, effect size calculation, survival analysis, and ROC analysis.
Serve Llama 2 and other large language models locally from command line or through a browser interface.
Oml is an OCaml math library that collects OCaml math and statistics functions. It aims for a descriptive, simple and typed approach to algorithms. A superset, Oml_full, includes C and Fortran dependencies such as Lacaml and LBFGS.
OneComp is a Python package for large language model (LLM) compression, hosted as a public repository under the FujitsuResearch GitHub organization. The project is designed for LLM compression tasks and accepts community contributions to its codebase.
ONNX-MLIR provides compiler technology that transforms a valid Open Neural Network Exchange (ONNX) graph into code implementing the graph with minimum runtime support. It is based on LLVM/MLIR compiler technology and contributes an ONNX Dialect and a driver that lower ONNX graphs into MLIR files or LLVM bytecodes.
A library that enables training PyTorch models with differential privacy.
Open Foam Dev is a GitHub repository or organization with source code, releases, documentation, or project resources.
Open LLMs is a public repository that curates a list of open large language models (LLMs) available for commercial use. It also includes related datasets for LLM pre-training, instruction-tuning, and alignment-tuning, and is hosted under the eugeneyan GitHub organization.
This GitHub repository hosts the open-source release of xAI's Grok-1 model. It provides model specifications, guidance for downloading model weights, associated license information, and accepts community contributions to the project.
Open Vsp is a GitHub repository or organization with source code, releases, documentation, or project resources.
A repository archived by its owner and now read-only. It is an open solution to the TGS Salt Identification Challenge. The project is listed with data science and image segmentation topics. The readme states that support can no longer be provided.
This GitHub repository hosts an open solution for the Airbus Ship Detection Challenge. It outlines the project's goals, includes a disclaimer, provides guidance for getting started, and shares information about the implemented solutions, while accepting community contributions.
This GitHub repository contains an open solution for the Kaggle Toxic Comment Classification Challenge. It includes starter code for the challenge, documents the project's core idea, notes ensemble prediction capabilities, includes a disclaimer, and accepts community contributions.
This GitHub repository hosts an open solution for the Santander Value Prediction Challenge. It outlines the project's goals, includes a disclaimer, provides guidance for getting started, and links to related competition resources, while accepting community contributions.
OpenAGI is an open-source GitHub project for AI agent creation, described as a tool where large language models meet domain experts. It provides documentation for getting started, installation steps, usage guidance, and information for contributing to the project.
Evals is a framework for evaluating large language models and systems built using LLMs. It offers an existing registry of evals to test different dimensions of OpenAI models and the ability to write custom evals. It is available as an open-source registry of benchmarks. Evals require an OpenAI API key.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
OpenCalc is a GitHub repository or organization with source code, releases, documentation, or project resources.
Open Code Review is an AI-powered code review CLI tool that reads Git diffs and sends changed files to a configurable LLM agent, producing structured line-level review comments. It also scans entire files and supports OpenAI and Anthropic compatible endpoints.
