Projects sharing features with Llm Viz

SHAP is a machine learning explainer that uses a game-theoretic framework to estimate the contribution of each feature to a model prediction. It provides a set of tools for quantifying how individual input features push a specific output away from a baseline value. The project includes specialized explainers for different architectures, including high-speed implementations for decision trees and ensemble models, linearization algorithms for deep learning networks, and covariance integration for linear models. It also features a model-agnostic interpretability tool that uses a kernel method to

Lit is a machine learning interpretability framework and model debugging tool designed to analyze model behavior and performance. It serves as an interpretability dashboard for large language models and a general performance analyzer for text, image, and tabular datasets. The project distinguishes itself through a comprehensive suite of interpretability tools, including salience map generation for feature attribution, the creation of synthetic and counterfactual examples to test robustness, and the projection of high-dimensional embeddings into visual spaces via UMAP or PCA. It further enable

Scanopy is a self-hosted infrastructure inventory and network discovery tool. It identifies hosts, services, and workloads across subnets to build a live model of network infrastructure, maintaining a searchable catalog of assets. The system features an interactive network topology visualizer that generates physical, logical, and application dependency diagrams. It maps the nesting chain from physical hardware and hypervisors down to virtual machines and containers, utilizing SNMP for hardware metadata and container APIs for workload discovery. The platform supports distributed network scann

This project is a collection of interactive graphical tools designed for monitoring neural network training, latent space mappings, and the internal mechanisms of transformers. It functions as a visual learning environment for understanding how large language models process tokens and an educational tool for analyzing the interactions between generators and discriminators within adversarial networks. The system provides a browser-based transformer architecture visualizer to show the mathematical operations used for token prediction in real time. It also includes a generative adversarial netwo

Gitdiagram is a software architecture visualization tool that generates interactive diagrams from repository file hierarchies. By performing automated static code analysis, the system maps file structures and component dependencies to provide a visual representation of how different modules relate within a codebase. The platform functions as a searchable documentation catalog, allowing users to discover and explore architectural visualizations of public repositories. It combines server-side rendering for initial delivery with a client-side engine that enables users to dynamically manipulate a

gemma.cpp is a C++ inference engine for Gemma, PaliGemma, and Griffin language models, designed to run directly on-device without Python dependencies. It provides a self-contained runtime that loads quantized model weights and performs text generation on CPU or GPU, along with a model checkpoint converter that transforms PyTorch or Keras checkpoints into a compact binary format for fast loading. The engine supports multiple model architectures, including the Griffin recurrent architecture with gated linear recurrent layers and sliding-window attention for efficient long-sequence handling, as

Interpret is an interpretable machine learning library and glassbox model framework. It provides toolkits for training inherently transparent models and applying post-hoc explanation techniques to make machine learning predictions human-understandable. The framework distinguishes itself by integrating differential privacy into the training of interpretable models to prevent sensitive data from leaking through explanations. It also features a visualization tool for rendering interactive decision paths and model behavior. The library covers model explainability through feature importance calcu

InterpretableMLBook is a comprehensive Chinese translation of the guide to understanding and explaining black-box machine learning models. It serves as a technical reference and manual for applying model-agnostic techniques to interpret the internal logic of complex algorithms. The resource focuses on black-box model analysis, providing a systematic approach to explaining individual predictions using methods such as Shapley values and LIME. It covers the evaluation of different interpretation methods to determine the most appropriate technique for a given project. The content is organized in

nlp-recipes is a collection of implementation guides and reference templates for applying natural language processing techniques to real-world tasks. It provides standardized workflows and code examples for developing NLP pipelines, from dataset preparation and model training to performance evaluation. The project focuses on the practical application of transformer-based models, offering patterns for fine-tuning pretrained architectures for tasks such as text classification, named entity recognition, and question answering. It also includes a toolkit for model interpretability, allowing users

Netron is a visualizer for neural network and machine learning models. It provides a graphical interface that renders model architectures as interactive node-link diagrams, allowing users to inspect internal layers, tensors, and metadata. By performing static analysis, the tool enables the examination of model definitions without executing the underlying machine learning code. The software distinguishes itself through a schema-driven parsing engine that translates diverse proprietary model formats into a unified internal graph structure. This approach ensures interoperability, allowing users

model-viewer is a web-based 3D model viewer provided as a web component for rendering interactive three-dimensional assets and animations directly in a browser. It functions as a specialized GLTF web renderer designed to display GLTF and GLB files with settings optimized for performance and quality. The project includes a WebXR augmented reality player that projects 3D models into real-world environments using mobile device cameras and spatial tracking. It also features a visual regression testing tool capable of generating golden images and comparing renders to detect visual regressions in 3

Viser is a Python 3D visualization framework and remote scene server that renders 3D primitives, point clouds, and meshes in a web browser. It functions as a server-client system that synchronizes scene state and camera poses to a web client via WebSockets. The framework provides specialized capabilities for robotics and computer vision, including a URDF robot visualizer for loading robot models and joint states, as well as a GPU-accelerated Gaussian splatting viewer for high-fidelity volumetric rendering. It also supports the visualization of human body models and skinned meshes for pose ana

cnn-explainer is an interactive web application and educational sandbox designed for visualizing the internal operations and layers of convolutional neural networks. It functions as a tool for understanding how these networks process image data through real-time graphics and interactive visualizations. The project includes a browser-based environment for training small convolutional neural networks on specific image classes. It also provides a model converter that transforms trained neural network files from backend framework formats into web-compatible versions for browser loading. The appl

Rerun is a multimodal data visualizer and robotics data logger designed for rendering synchronized streams of 3D spatial data, images, and time-series metrics. It functions as a tool for capturing high-frequency sensor data and AI outputs into a queryable columnar format, providing a dedicated interface for viewing MCAP recording files and analyzing physical environments. The project distinguishes itself as a machine learning dataset streamer, capable of feeding logged recordings directly into GPU buffers and PyTorch training pipelines without intermediate exports. It supports a high-performa

This project is an educational resource focused on the internal mechanics and design principles of transformer-based neural networks. It provides a structured guide to the fundamental components of generative artificial intelligence, including sequence modeling, semantic embeddings, and the mathematical foundations of large language models. The repository distinguishes itself through a heavy emphasis on visual documentation, utilizing diagrams and step-by-step explanations to clarify how data flows through complex neural architectures. It serves as a technical reference for developers seeking

LWJGL is a cross-platform library that provides Java bindings to native APIs for graphics, audio, compute, windowing, and input. It enables Java applications to access low-level hardware-accelerated capabilities such as OpenGL and Vulkan rendering, OpenAL 3D audio, OpenCL GPU compute, and GLFW windowing and input handling. Under the hood, LWJGL dynamically resolves native function pointers at runtime, loads platform-specific shared libraries, and uses generated JNI bindings to bridge Java and native code. It offers explicit memory management through direct buffer access and stack-allocated me

DirectXTK is a C++ library designed to simplify 2D and 3D graphics, audio, and input programming for DirectX applications. It serves as a comprehensive toolkit providing high-level wrappers for DirectX graphics, audio management, and input handling. The toolkit includes a graphics wrapper for loading textures and rendering 3D models and 2D sprites, alongside a dedicated audio manager for sound effects and 3D spatial audio. It also provides an input handler to track and process state updates from keyboards, mice, and gamepads. The library covers a broad capability surface including 3D math an

gsplat is a high-performance differentiable rasterization engine for 3D Gaussian splatting, designed for real-time novel view synthesis from 2D images. It provides a complete pipeline for reconstructing 3D scenes by optimizing differentiable Gaussian representations, training models from COLMAP-processed captures or proprietary device files, and generating new viewpoints through a CUDA-accelerated rendering backend. The framework distinguishes itself through memory-optimized CUDA kernels that reduce training memory usage by up to 4x compared to standard implementations while matching publishe

model-viewer is a web component used to render and interact with three-dimensional models directly in a web browser. It functions as a glTF 3D model renderer and an interactive WebGL component, encapsulating a 3D rendering pipeline within a custom HTML element. The project enables web-based augmented reality, allowing 3D assets to be projected into physical environments using a mobile device camera. It provides tools for augmented reality projection and experience creation by combining 3D models with camera tracking. The component supports 3D product visualization and the integration of inte

This project is a frontend visualization library and gallery of interactive web examples. It provides a collection of implementations that demonstrate advanced visual effects through the use of stylesheets, canvas drawing surfaces, and three-dimensional graphics libraries. The collection specifically features implementations for visualizing artificial intelligence outputs and complex data patterns. It includes specialized galleries for three-dimensional scenes and spatial objects, as well as a showreel of stylistic motion effects and interface designs. The library covers a broad range of ren

mini-tokyo-3d is a 3D transit map visualization system that renders public transport networks and vehicle movements in real time using open data. It functions as a real-time transit tracker and an interactive transport route finder, providing a WebGL map embed that can be integrated into web pages and external applications. The system features a multilingual transit interface that translates transport identifiers and navigation elements into multiple languages. It tracks vehicle positions by simulating movements based on live timetables and service delay information. The project covers publi

Neuralforecast is a neural time series forecasting library designed to predict future values for one or multiple series using deep learning architectures. It functions as a distributed machine learning forecasting framework that enables the training of global models across multiple time series to improve generalization through cross-learning. The project distinguishes itself as a probabilistic forecasting toolkit that produces uncertainty intervals and probability distributions rather than single point estimates. It also includes a hierarchical forecast reconciler to ensure that predictions a

GPAC is an open-source multimedia framework built around a pluggable filter graph pipeline, where modular processing units called filters connect into a directed graph to handle media workflows. At its core, the framework centers all media packaging and manipulation on the ISO Base Media File Format (ISOBMFF), with specialized tools for reading, writing, fragmenting, and encrypting MP4 and related containers. It also provides a declarative scene graph composition system for describing interactive multimedia scenes using MPEG-4 BIFS, X3D, SVG, or VRML syntax, alongside a hardware-accelerated re

PyTorch3D is a 3D geometric deep learning library and mesh processing toolkit designed for learning from point clouds and complex 3D surface geometries. It provides a collection of reusable components and data structures for deep learning with 3D data, including a framework for training and evaluating neural radiance fields to enable photorealistic view synthesis. The project features a differentiable 3D renderer that converts meshes and point clouds into 2D images while allowing gradients to flow back into the geometry and textures. This enables 3D shape optimization, where mesh geometry, te

ubuntu-rockchip is a Rockchip Ubuntu distribution and GPU-accelerated Linux image designed for RK35XX series single-board computers. It provides a 64-bit ARM64 Linux environment that deploys a standard Ubuntu desktop on top of specialized board-support packages. The system features hardware drivers for 3D graphics acceleration and 4K video rendering and streaming. These optimizations allow for high-resolution media playback and increased rendering speeds for 3D applications on Rockchip hardware. The distribution includes tools for single-board computer administration, such as a guided first-

f3d is a fast 3D model viewer and rendering engine designed for visualizing 3D meshes, CAD files, and point clouds. It operates across multiple deployment profiles, functioning as a lightweight desktop application, a scientific data visualizer for volumetric and scalar datasets, a headless rendering engine for automated image generation, and a WebAssembly-based renderer for web applications. The project distinguishes itself through specialized support for Gaussian Splatting scene reconstructions and the ability to visualize complex scientific formats such as VTK, NetCDF, and HDF. It features

XGBoost is a distributed machine learning library for implementing scalable gradient boosting decision trees used for regression, classification, and ranking. It functions as a predictive model framework and a cross-language toolkit, providing a core implementation with native bindings for Python, R, Java, Scala, and C++. The system is designed as a GPU-accelerated library that utilizes CUDA and NCCL to speed up the training of decision tree ensembles. It operates as a distributed framework capable of scaling training and prediction across multi-node clusters and GPU environments to process m