Coding & Development

D's Machine Learning (dml) is an open-source machine learning toolkit for Python, built upon the robust foundations of NumPy and SciPy. It emphasizes both the correctness of its algorithms and computational efficiency. The toolkit includes a comprehensive set of machine learning implementations, such as Neural Networks, Logistic Regression (softmax), Decision Trees (CART algorithm), and various clustering algorithms including k-means, k-medoids, spectral clustering, and hierarchical clustering. Additionally, it features Adaboost, k-Nearest Neighbor (with kd-tree BBF), Naive Bayesian (supporting continuous and discrete features), Support Vector Machines, simple Convolutional Neural Networks, and Collaborative Filtering algorithms. The project currently supports Python 2, with a note that Python 3 users are not yet supported.

The Llm Contamination Detector is a specialized tool hosted on Hugging Face Spaces, developed by Yeyito, aimed at identifying potential contamination within large language models (LLMs). This tool is crucial for maintaining the integrity and reliability of AI models, particularly in research and development environments. By detecting contamination, it helps ensure that LLMs are trained on clean, unbiased datasets, leading to more accurate and trustworthy AI outputs. While the live website currently indicates a runtime error, its intended purpose is to provide a valuable resource for AI researchers and machine learning engineers who need to validate the quality and purity of their language models. The tool's availability on Hugging Face Spaces suggests an open and community-driven approach to AI development.

DeepIE is an open-source deep learning framework specifically designed for information extraction tasks. It offers comprehensive implementations and benchmarks for key natural language processing (NLP) challenges such as named entity recognition (NER), relation extraction, and event extraction. The repository includes detailed performance metrics across various datasets and methods, including comparisons with BERT and other lexicon-enhanced models. DeepIE also provides resources like curated lists of relevant research papers and information extraction competitions, making it a valuable tool for researchers and developers working on advanced NLP applications.

DeepSeek-Coder-V2 is an advanced open-source Mixture-of-Experts (MoE) code language model, designed to rival the performance of leading closed-source models such as GPT4-Turbo in code-specific tasks. Built upon an intermediate checkpoint of DeepSeek-V2 and further pre-trained with an additional 6 trillion tokens, it significantly enhances coding and mathematical reasoning while maintaining strong general language capabilities. The model supports an extensive range of 338 programming languages and features an extended context length of 128K. It offers functionalities for code generation, code completion, and code fixing, demonstrating superior performance in various benchmarks. DeepSeek-Coder-V2 is available in 16B and 236B parameter versions, including base and instruct models, and can be accessed via HuggingFace, an OpenAI-compatible API, or run locally.

DFloat11 is an open-source, lossless compression framework designed to optimize Large Language Models (LLMs) and diffusion models for efficient GPU inference. It achieves approximately 30% reduction in model size without sacrificing accuracy, ensuring bit-for-bit identical outputs compared to the original models. The framework utilizes Huffman coding of BFloat16 exponent bits and hardware-aware algorithmic designs for on-the-fly decompression directly on the GPU. This approach eliminates CPU decompression and host-device data transfer, keeping weights compressed in GPU memory and decompressing them just before matrix multiplications. DFloat11 supports efficient inference on resource-constrained hardware, offering significant speed advantages over CPU-offloading methods, especially at larger batch sizes. It is compatible with CUDA-enabled GPUs and PyTorch.

Exia Labs specializes in developing AI-enabled command and control products, shifting the paradigm from language-only AI to spatial AI. Their technology is designed to master raw data from the physical world, creating machine-readable environments. This enables autonomous systems and AI agents to comprehend movement, constraints, and environmental effects. The primary goal is to provide warfighters and industry professionals with decision advantage by offering a clear understanding of locations, movements, and future events. Exia Labs aims to build the architectural foundation for this advanced spatial AI, moving beyond traditional analog tools and text-focused AI solutions.

Make Custom Voices With KokoroTTS is a web-based tool hosted on Hugging Face Spaces, designed for creating unique voice profiles. It enables users to select from several pre-made voices, fine-tune their individual strengths using intuitive sliders, and then blend them together to form a single, custom voice. Once a custom voice is created, users can input any text, and the application will read it aloud using their newly mixed voice. This tool is ideal for experimenting with voice synthesis and exploring different vocal textures and tones.

exBERT is an open-source visual analysis tool designed to help users explore and understand the learned attention weights and contextual representations within various Hugging Face Transformer models. It supports models like BERT, GPT2, DistilBERT, and ALBERT. Users can input sentences, visualize attention patterns as curved lines, and search embeddings across an annotated corpus. Key features include toggling visibility of attention to [CLS] and [SEP] tokens, interactively masking tokens to observe attention changes, and viewing model predictions. It also allows searching for contextual representations of tokens across layers and discovering linguistic features learned by specific heads, making it an invaluable resource for AI researchers and NLP developers.

EvalPlus is a comprehensive and rigorous evaluation framework designed for Large Language Models (LLMs) that generate code. It significantly expands upon existing benchmarks, offering HumanEval+ with 80x more tests and MBPP+ with 35x more tests than their original versions, ensuring a more precise assessment of code correctness. Additionally, EvalPerf evaluates the efficiency of LLM-generated code through performance-exercising tasks and test inputs. The framework supports various LLM backends, including HuggingFace, vLLM, OpenAI-compatible servers, Anthropic, Google Gemini, Amazon Bedrock, and Ollama, allowing for flexible integration. EvalPlus enables developers and researchers to benchmark LLMs, identify fragile code generations, and understand performance beyond mere correctness, making it a critical tool for advancing code AI.

Evaluate is a comprehensive open-source library designed to simplify the evaluation and comparison of machine learning models and datasets. It offers a wide array of pre-implemented metrics covering tasks from Natural Language Processing to Computer Vision, including dataset-specific metrics. Users can easily load and apply these metrics across different ML frameworks like NumPy, Pandas, PyTorch, TensorFlow, and JAX. The library also facilitates comparisons between models and provides tools for dataset evaluation. A key feature is the ability to add new evaluation modules to the Hugging Face Hub, fostering community collaboration and allowing users to share and discover custom metrics. Evaluate includes type checking for inputs, detailed metric cards explaining usage and limitations, and supports community-driven metric development.

DSPy is an open-source framework designed to program, rather than merely prompt, language models. It enables developers to build modular AI systems efficiently, offering algorithms to optimize prompts and weights for improved performance. Whether creating simple classifiers, sophisticated Retrieval-Augmented Generation (RAG) pipelines, or complex agent loops, DSPy provides a structured approach. The framework, which stands for Declarative Self-improving Python, allows users to write compositional Python code, teaching the language model to deliver high-quality outputs consistently. It aims to replace brittle prompting methods with a more robust, programmatic paradigm for AI development.

DualPipe is an innovative open-source algorithm designed for efficient training of large language models, specifically DeepSeek V3/R1. It introduces a bidirectional pipeline parallelism approach that fully overlaps forward and backward computation-communication phases, significantly reducing pipeline bubbles. This optimization leads to more efficient use of computational resources during deep learning model training. The project also offers DualPipeV, a concise V-shape schedule derived from DualPipe, further enhancing efficiency. Developers can integrate DualPipe into their PyTorch 2.0+ projects, with examples provided for quick start. It's particularly useful for those working on large-scale model training where communication overhead is a critical factor.

EasyEdit is an open-source framework designed for knowledge editing in Large Language Models (LLMs). It offers an easy-to-use interface for developers to modify and control the information LLMs know and how they behave. The framework supports a wide array of knowledge editing techniques, ranging from updating internal parameters and introducing additional parameters (EasyEdit 1.0) to real-time steering during inference without retraining (EasyEdit 2.0). It integrates various steering methods and provides tools for evaluation, including a hierarchical benchmark called SteerEval. EasyEdit also incorporates support for unstructured long-form knowledge editing datasets and methods, making it a comprehensive solution for researchers and developers working on LLM controllability and refinement.

CrayEye, formerly PromptBoost AI Prompt Engineer, is a multimodal multitool designed to enhance interactions with AI chatbots by allowing users to craft and share sophisticated LLM vision prompts. This innovative platform integrates real-world context from device sensors and APIs, enabling AI to interpret environments in new ways. Users can experiment with visual multimodal models, customize prompts augmented by data like location and weather, and share their creations with others. The tool is free, open-source, and was developed using AI-driven methods, making it accessible for a wide range of users interested in advanced prompt engineering.

fastembed-rs is a Rust library designed for efficient generation of vector embeddings and reranking, crucial for building advanced AI applications. It offers synchronous usage and leverages @pykeio/ort for high-performance ONNX inference and @huggingface/tokenizers for rapid encodings. The library supports a wide array of pre-trained models for text embeddings (including BGE, MiniLM, MPNet, Nomic, and Qwen3 models), sparse text embeddings (like Splade_PP_en_v1 and BGE-m3), and image embeddings (such as CLIP, ResNet50, and Unicom models). Additionally, it provides reranking functionalities with models like BGE-reranker-base. Developers can easily integrate fastembed-rs into their Rust projects, with options for custom model initialization and support for DirectML on Windows for GPU acceleration.

The Model Memory Calculator, developed by TitanML, is a valuable tool hosted on Hugging Face Spaces designed to assist developers and data scientists in understanding the memory footprint of their AI models. By providing an estimate of the resources needed to run specific models, it facilitates better planning and optimization of AI deployments. This calculator is particularly useful for those working with large language models or complex neural networks, where memory management is crucial for efficient operation and cost-effectiveness. It helps users make informed decisions about hardware requirements and model architecture, ensuring their AI projects are both performant and resource-aware.

AyGLOO specializes in applying artificial intelligence to solve real-world business problems, creating tailored solutions that combine automation, language comprehension, and ethical responsibility. Their services include designing and implementing Agentic AI systems for autonomous task automation and information analysis, as well as Prescriptive Decision AI, which evaluates prediction reliability and calculates the expected impact of actions. AyGLOO's approach ensures that AI systems are explainable, traceable, and auditable, providing tangible results for clients across various sectors. They have a proven track record with projects for companies like Bidafarma, Suzuki, and PwC, demonstrating their ability to transform businesses through AI.

DRL-FlappyBird is an open-source project designed to showcase deep reinforcement learning principles through the classic game Flappy Bird. It implements the Deep Q Learning (DQN) algorithm, specifically leveraging TensorFlow for its neural network computations. The project aims for simplicity and clarity, making the underlying DQN code concise and easy to understand, at only 160 lines long. It includes both the NIPS 2013 and Nature Version DQN implementations. The modular design allows the core DQN class to be adapted for playing other games, providing a flexible framework for reinforcement learning experimentation. Users can easily run the code to observe an AI agent learning to play Flappy Bird.

Dromedary is an open-source, self-aligned language model developed by IBM, designed to create helpful, ethical, and reliable Large Language Models (LLMs) with minimal human supervision. It features a principle-driven self-alignment process, including the updated Dromedary-2 (SFT) which utilizes diverse user prompts and an improved prompt structure for enhanced performance. Dromedary-2 also introduces the SALMON (Self-ALignMent with principle-fOllowiNg reward models) training pipeline for RLAIF. The project provides model weights as delta weights for LLaMA, synthetic data for self-alignment, and a full training pipeline for reproduction, making it a valuable resource for researchers and developers in the NLP domain.

DPM-Solver is an open-source code library providing a fast, high-order ODE solver specifically designed for diffusion probabilistic model sampling. It includes DPM-Solver and the improved DPM-Solver++, both offering convergence order guarantees without requiring further training. This tool significantly accelerates the sampling process, capable of generating high-quality samples with only 10 to 20 function evaluations across various datasets. It supports both discrete-time and continuous-time diffusion models and is integrated into popular libraries like Hugging Face Diffusers, making it accessible for applications such as Stable-Diffusion, DeepFloyd-IF, and image editing tasks like DiffEdit. The library supports various model types (noise, data, velocity prediction, score function) and sampling types (unconditional, classifier guidance, classifier-free guidance), offering flexibility for developers working with diffusion models.

GenAIExamples is an Open Source project providing a collection of generative AI examples, including applications like ChatQnA and Copilot. It is designed to offer developers an accessible entry point into generative AI by featuring microservice-based samples that streamline the deployment, testing, and scaling of GenAI applications. The examples are fully compatible with both Docker and Kubernetes, ensuring flexibility across various environments. It supports a wide range of hardware platforms, including Gaudi, Xeon, AMD EPYC CPUs, AMD Instinct GPUs, and NVIDIA GPUs. The project also includes GenAIComps for microservice components, GenAIInfra for cloud-native deployment, and GenAIEval for performance metrics, making it a comprehensive toolkit for GenAI adoption.

All-in-One Demo is an AI demonstration tool hosted on Hugging Face Spaces, designed to showcase various AI functionalities. It is built using Gradio, an open-source Python library for creating easy-to-use UI components for machine learning models. This tool is intended for individuals, developers, and researchers who wish to explore and test different AI models and applications. While the live website indicates a runtime error, suggesting it may not be currently operational, its purpose is to provide a platform for interacting with AI models. It is licensed under AFL-3.0, making it accessible for free use and modification.

ARGEDOR Information Technologies is a company dedicated to helping businesses harness the full potential of blockchain technology. They provide advanced solutions across various industries, specializing in Web3, Metaverse, and Artificial Intelligence. Their blockchain services include the creation of NFTs, NFT marketplaces, DeFi/GameFi applications, DAOs, and dApps. For the Metaverse, ARGEDOR offers a cutting-edge Web3 engine for building, managing, and monetizing virtual worlds. Additionally, they develop AI-based solutions to address contemporary business challenges, leveraging expertise in ML/DL/AI and data analytics. ARGEDOR supports clients from ideation to execution, serving startups to large enterprises.

Generative_Deep_Learning_2nd_Edition is the official code repository for the second edition of the O'Reilly book "Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play." This open-source resource provides practical code examples and outlines corresponding to the book's chapters, covering topics such as Variational Autoencoders, Generative Adversarial Networks, Autoregressive Models, Normalizing Flows, Energy-Based Models, Diffusion Models, Transformers, and advanced GANs. It is designed to help users learn and implement generative deep learning techniques, with instructions for setting up a Docker environment, downloading datasets, and using Tensorboard for monitoring experiments. The repository also includes guidance for using cloud virtual machines.