Coding & Development

Lightwood is an AutoML framework designed to streamline the machine learning (ML) lifecycle by allowing users to generate and customize ML pipelines through a declarative syntax called JSON-AI. It abstracts the ML pipeline into three core steps: pre-processing and data cleaning, feature engineering, and model building and training. Lightwood automatically identifies data types, performs cleaning, and splits data. It supports various data types including numbers, dates, categories, text, and multimedia, and offers a time-series mode. Users can override default behaviors, customize encoders, and integrate their own models, making it highly flexible for unique and custom ML tasks. The framework generates Python code from JSON-AI objects, enabling end-to-end training and prediction with pandas DataFrames.

llama3.np offers a pure NumPy implementation of the Llama 3 model, making it an excellent resource for researchers and developers interested in understanding the underlying architecture of large language models. The project was validated using the stories15M model trained by Andrej Karpathy, ensuring an accurate and reliable implementation. It provides a straightforward way to run the Llama 3 model using Python and NumPy, demonstrating the core mechanics without complex dependencies. This tool is particularly valuable for academic research and educational contexts, allowing for detailed exploration and experimentation with the Llama 3 model's components.

LION (Latent Point Diffusion Models for 3D Shape Generation) is an open-source project presented at NeurIPS 2022, offering a robust framework for generating 3D shapes. This tool leverages advanced diffusion models to create 3D point clouds, enabling researchers and developers to explore and innovate in the field of 3D content creation. It includes functionalities for training VAE and diffusion prior models, with options for conditioning inputs like CLIP image embeddings for tasks such as single-view reconstruction or text-to-shape generation. The project provides detailed installation instructions, demo scripts, and evaluation tools, making it a valuable resource for those working with 3D shape synthesis and analysis.

LightReasoner is an innovative open-source research tool that redefines how large language models (LLMs) acquire reasoning capabilities. It leverages small language models (SLMs) to strategically identify critical reasoning moments, allowing LLMs to focus their learning more efficiently. This approach achieves superior performance with remarkable token efficiency, reducing total training time by 90%, sampled problems by 80%, and tuned tokens by 99% compared to traditional Supervised Fine-Tuning (SFT). The framework consists of a three-stage process: critical step selection via Expert-Amateur KLD detection, contrastive supervision, and self-distillation. LightReasoner demonstrates that strategic token selection, rather than exhaustive training, is key to unlocking latent LLM reasoning potential, proving that smarter, not blindly harder, is the path to scalable AI improvement.

LightCompress is an open-source toolkit designed for compressing large AI models such as Large Language Models (LLMs), Vision-Language Models (VLMs), and video generative models. It offers a comprehensive suite of state-of-the-art compression algorithms, including various quantization methods (integer, floating-point, mixed-precision) and sparsity techniques (structured, unstructured). The tool supports a wide array of popular models like LLaMA, Mistral, and DeepSeekv2, and ensures compatibility with multiple inference backends such as VLLM, Sglang, and AutoAWQ. LightCompress aims to significantly reduce model size and improve inference efficiency while maintaining high accuracy, making it ideal for deploying large models on resource-constrained hardware.

DCRNN (Diffusion Convolutional Recurrent Neural Network) is an open-source project offering a TensorFlow implementation of the Diffusion Convolutional Recurrent Neural Network model. This tool is specifically designed for data-driven traffic forecasting, as detailed in the ICLR 2018 paper by Li et al. It allows users to prepare traffic data, construct graphs based on sensor networks, and train or run pre-trained models for prediction. The repository includes scripts for data preparation, graph generation, and model training on datasets like METR-LA and PEMS-BAY. Beyond traffic, DCRNN's variants have been applied to neuroimaging, air quality forecasting, and internet traffic forecasting, showcasing its versatility in spatiotemporal forecasting tasks.

d2l-pytorch is an open-source project that meticulously reproduces the content of the acclaimed "Dive Into Deep Learning" book, translating its original MXNet code examples into PyTorch. This adaptation offers students and researchers a valuable resource for understanding and implementing deep learning concepts using the widely adopted PyTorch framework. The repository covers a comprehensive range of topics, from foundational preliminaries like data manipulation and linear algebra to advanced subjects such as convolutional neural networks, recurrent neural networks, attention mechanisms, and various optimization algorithms. It serves as a practical, hands-on guide for learning deep learning through code.

llama-swap is a robust AI Agents & Automation tool designed for reliable model swapping across local OpenAI and Anthropic compatible servers, including llama.cpp and vllm. It allows users to run multiple generative AI models on their machine and hot-swap between them on demand. Built in Go for performance and simplicity, llama-swap boasts zero dependencies and is incredibly easy to set up with just one binary and one configuration file. It supports a wide range of OpenAI and Anthropic API endpoints, as well as specific endpoints for llama-server and SDAPI. The tool also includes a real-time web UI with a playground for testing models, viewing token metrics, and monitoring logs, making it a comprehensive solution for managing local AI workflows.

The Label Studio ML backend is an SDK designed to transform your machine learning code into a web server. This server seamlessly integrates with a running Label Studio instance, enabling the automation of diverse labeling tasks. It supports a wide array of models, including text classification with Huggingface and scikit-learn, object detection with YOLO and Grounding DINO, NER with Flair and SpaCy, and OCR with EasyOCR and PaddleOCR. Developers can implement custom prediction and training logic, leveraging helper methods for data storage and retrieval. The SDK provides examples for quick setup and deployment options to platforms like GCP, making it a versatile tool for integrating ML into data annotation workflows.

MachineLearningNotebooks is a GitHub repository offering Python notebooks filled with machine learning and deep learning examples, specifically designed for use with the Azure Machine Learning Python SDK. This resource provides practical demonstrations for various tasks, including building, training, and deploying machine learning models within the Azure ecosystem. While this repository focuses on the v1 SDK, it serves as a valuable historical reference for developers and data scientists working with Azure ML. Users are encouraged to explore the v2 SDK samples repository for the most current and enhanced examples, as this v1 repository is deprecated and no longer actively monitored or updated.

llm-ui is an open-source React library specifically designed for integrating Large Language Models (LLMs) into user interfaces. It simplifies the process of displaying and interacting with LLM outputs, offering features like the ability to add custom components to the LLM's streamed responses. The library also includes throttling to smooth out pauses in streamed output, ensuring a native frame rate rendering experience. It provides robust support for code blocks across various programming languages using Shiki, and its headless nature allows developers to bring their own styles for complete UI customization. This makes llm-ui a flexible solution for developers looking to build dynamic and responsive AI-powered applications.

llm.pdf is a proof-of-concept project showcasing the ability to run an entire Large Language Model (LLM) within a PDF file. This innovative approach leverages Emscripten to compile llama.cpp into asm.js, enabling the LLM to execute directly within the PDF environment through an old PDF JS injection method. The entire LLM file is embedded into the PDF using base64 encoding, allowing for self-contained LLM inference. While currently a proof-of-concept, it highlights the potential for highly portable and self-sufficient AI applications. Users can generate custom PDFs with compatible GGUF quantized models, with 135M parameter models taking approximately 5 seconds per token for input/output.

Chat-fu is a Coding & Development tool designed to help individuals and small businesses create a professional online presence with integrated AI capabilities. It focuses on simplifying the process of building a portfolio page that includes an interactive AI chatbot. This tool aims to make website creation accessible, even for users without extensive coding knowledge, by providing a streamlined platform to establish an online presence quickly and efficiently. The integration of an AI chatbot allows for enhanced user engagement and a more dynamic website experience, catering to those looking to showcase their work or services with modern, interactive features.

long-context-attention, also known as Unified Sequence Parallelism (USP) or Hybrid Sequence Parallelism, offers a novel approach to training and inference for long context Large Language Models (LLMs). This open-source project synergizes the strengths of DeepSpeed-Ulysses-Attention and Ring-Attention, addressing their individual limitations. Ulysses-Attention is sensitive to the number of attention heads and less suitable for GQA/MQA scenarios, while Ring-Attention can be less efficient in computation and communication. LongContextAttention provides a more general, versatile, and performant solution. It supports various FlashAttention versions (v2, v3) and can even run without FlashAttention for NPUs. The tool includes functionalities for setting process groups, extracting local tensors, and offers different ring implementation types like 'zigzag' and 'basic'. It has been verified in Megatron-LM and applied in several other projects, providing a robust solution for researchers and developers working with long context generative AI.

DDNM, or Denoising Diffusion Null-Space Model, is a cutting-edge AI tool for zero-shot image restoration, presented at ICLR 2023. It excels at solving a wide range of image restoration tasks, including super-resolution, denoising, colorization, inpainting, deblurring, and compressed sensing, all without requiring specific optimization or training. The tool supports arbitrary image sizes and offers both an SVD-based version for precise noisy tasks and a simplified version for flexible user-defined degradations. DDNM also provides functionalities for real-world applications like old photo restoration and enhancing degraded images, allowing users to define degradation operators and noise levels for customized results.

Alrite is a company dedicated to developing innovative AI applications, with a current focus on tools such as Rizzpad and PetCoco. These applications are crafted to streamline and enhance various aspects of daily life for users. Alrite emphasizes creating user-friendly AI solutions that are accessible and beneficial for a wide range of consumer applications. The company aims to integrate artificial intelligence seamlessly into everyday routines, making advanced technology practical and easy to use for everyone.

LookaheadDecoding is an open-source project designed to significantly accelerate Large Language Model (LLM) inference by breaking the traditional sequential dependency of token generation. This innovative approach utilizes a parallel decoding algorithm, eliminating the need for a draft model or a separate data store. Motivated by Jacobi decoding, LookaheadDecoding collects and caches n-grams from Jacobi iteration trajectories, enabling simultaneous processing of future tokens. The process is divided into a lookahead branch, which generates new n-grams within a defined window, and a verification branch, which validates promising candidates. This method has demonstrated substantial latency reductions, achieving speedups ranging from 1.5x to 2.3x on various datasets and models. The tool supports sampling and FlashAttention, and is implemented with an attention mask to maximize GPU parallel computing power, making it a valuable resource for optimizing LLM performance.

Data-science-on-aws is an open-source resource designed to educate users on implementing AI and Machine Learning solutions within the Amazon Web Services (AWS) ecosystem. It provides comprehensive examples for constructing end-to-end AI/ML pipelines, leveraging powerful tools such as Kubeflow, Amazon EKS, and Amazon SageMaker. The resource is structured around an O'Reilly book, offering practical, hands-on demonstrations. Users will learn to train and tune BERT models for natural language processing, perform hyper-parameter tuning, A/B testing, and set up real-time streaming analytics. It covers data ingestion, exploration, preparation, model training, optimization, deployment, and security, making it ideal for those looking to master data science workflows on AWS.

Deep-Learning-in-Production is a comprehensive GitHub repository curated by ahkarami, designed to serve as a valuable resource for deploying deep learning-based models in production environments. The repository compiles useful notes and references across various deep learning frameworks, including PyTorch, TensorFlow, Keras, and MXNet. It covers essential topics such as model conversion (e.g., PyTorch to C++, Keras to C++), model serving with tools like Flask, TorchServe, and TensorFlow Serving, and deployment on platforms like AWS Lambda and Kubernetes. Additionally, it provides insights into model quantization, speed optimization, and general deep learning deployment toolkits like OpenVINO and NVIDIA Triton Inference Server. The repository also includes resources for front-end and back-end development, mobile/embedded device deployment, and MLOps, making it a holistic guide for machine learning engineers and data scientists looking to operationalize their models.

deep-learning-wizard offers open-source guides and code for mastering deep learning, from foundational concepts to production deployment. The resource covers a wide array of topics including machine learning, deep learning, deep reinforcement learning, data engineering, and general programming. It provides tutorials on PyTorch, Python, Apptainer, and other relevant libraries, making it suitable for both beginners and those looking to deepen their expertise. The platform is designed to be mobile and tablet-friendly, ensuring accessibility for learners on various devices. It also includes sections on language models, HPC containers, and optimization techniques, aiming to provide a comprehensive learning experience for deep learning practitioners.

Mirage Persistent Kernel (MPK) is a compiler and runtime system designed to optimize large language model (LLM) inference by transforming it into a single, high-performance megakernel. This end-to-end GPU fusion approach significantly reduces LLM inference latency, offering improvements of 1.2× to 6.7× with minimal developer effort. MPK allows users to compile LLMs from the Hugging Face model zoo into a megakernel using Python, abstracting away complex CUDA/Triton programming. It provides an API for instantiating persistent kernels, attaching existing PyTorch tensors, and defining computation graphs by chaining fused operations. The tool is open source and aims to simplify the deployment of efficient LLM inference.

deepvoice3_pytorch provides a PyTorch implementation of convolutional neural networks for text-to-speech synthesis, based on the Deep Voice 3 architecture. It supports both multi-speaker and single-speaker models, offering pre-trained models and preprocessors for datasets like LJSpeech (English), JSUT (Japanese), and VCTK (English). The tool allows users to preprocess data, train models, and synthesize audio from text. It also includes features like guided attention, binary divergence for stable training, and support for custom datasets in JSON format. Users can monitor training progress with Tensorboard and utilize specific Git commits for compatibility with pre-trained models.

dev3000 is a debugging assistant designed to capture a comprehensive timeline of a web application's development process. It monitors and records server logs, browser console messages and errors, network requests and responses, and user interactions. Additionally, it takes automatic screenshots during navigation, errors, and interactions. All this data is organized into timestamped logs that AI assistants can readily understand, enabling them to identify issues and suggest accurate fixes with full context. The tool supports various web frameworks including JavaScript/TypeScript, Python, and Ruby, and can integrate with any AI assistant capable of reading files, such as Claude or OpenAI Codex. It offers diagnostic commands for error analysis, log viewing, and application crawling, making it a powerful aid for developers.

DeepMoji is a state-of-the-art deep learning model designed for analyzing sentiment, emotion, and sarcasm in textual data. The model was trained on an extensive dataset of 1.2 billion tweets, leveraging emojis to understand how language expresses various emotions. It offers transfer learning capabilities, allowing it to achieve state-of-the-art performance on numerous emotion-related text modeling tasks. Developers can use DeepMoji to extract emoji predictions, convert text into 2304-dimensional emotional feature vectors, or fine-tune the model for new datasets. The project is open-source and based on Keras, supporting either Theano or TensorFlow as a backend. A PyTorch implementation, torchMoji, is also available.