LLM Calculator is a script that estimates the memory requirements and performance of Hugging Face models based on quantization levels. It fetches model parameters, calculates required memory, and analyzes performance with different RAM/VRAM configurations. The tool supports Windows and Linux, AMD, Intel, and Nvidia GPUs. Users can input a Hugging Face model ID to get its parameter count and analyze memory requirements for various quantization schemes. The tool provides estimates for GPU offload percentage and throughput in tk/s. It requires dependencies like python, uv, pciutils for AMD + Linux, and drivers for Nvidia. The tool is designed for rough estimates and may not work with MultiGPU setups.

aiortc is a Python library for Web Real-Time Communication (WebRTC) and Object Real-Time Communication (ORTC). It provides a simple and readable implementation for programmers to understand and tinker with WebRTC internals. The library allows for exchanging audio, video, and data channels, supports SDP generation/parsing, ICE, DTLS, SRTP, SCTP, and various audio/video codecs. It also enables creating innovative products by leveraging Python ecosystem modules, such as computer vision algorithms with OpenCV. Extensive testing ensures high code quality.

Yalm (Yet Another Language Model) is an LLM inference implementation in C++/CUDA, emphasizing performance engineering, documentation, scientific optimizations, and readability. It is not for production use and has been tested on Mistral-v0.2 and Llama-3.2. Requires C++20-compatible compiler, CUDA toolkit, and LLM safetensor weights in huggingface format converted to .yalm file.

RAVE is a variational autoencoder for fast and high-quality neural audio synthesis. It can be used to generate new audio samples from a given dataset, or to modify the style of existing audio samples. RAVE is easy to use and can be trained on a variety of audio datasets. It is also computationally efficient, making it suitable for real-time applications.

Polymarket Agents is a developer framework and set of utilities for building AI agents to trade autonomously on Polymarket. It integrates with Polymarket API, provides AI agent utilities for prediction markets, supports local and remote RAG, sources data from various services, and offers comprehensive LLM tools for prompt engineering. The architecture features modular components like APIs and scripts for managing local environments, server set-up, and CLI for end-user commands.

ZipNN is a lossless and near-lossless compression library optimized for numbers/tensors in the Foundation Models environment. It automatically prepares data for compression based on its type, allowing users to focus on core tasks without worrying about compression complexities. The library delivers effective compression techniques for different data types and structures, achieving high compression ratios and rates. ZipNN supports various compression methods like ZSTD, lz4, and snappy, and provides ready-made scripts for file compression/decompression. Users can also manually import the package to compress and decompress data. The library offers advanced configuration options for customization and validation tests for different input and compression types.

The Ollama R library provides an easy way to integrate R with Ollama for running language models locally on your machine. It supports working with standard data structures for different LLMs, offers various output formats, and enables integration with other libraries/tools. The library uses the Ollama REST API and requires the Ollama app to be installed, with GPU support for accelerating LLM inference. It is inspired by Ollama Python and JavaScript libraries, making it familiar for users of those languages. The installation process involves downloading the Ollama app, installing the 'ollamar' package, and starting the local server. Example usage includes testing connection, downloading models, generating responses, and listing available models.

LlamaIndex is a data framework for building LLM applications. It provides tools for ingesting, structuring, and querying data, as well as integrating with LLMs and other tools. LlamaIndex is designed to be easy to use for both beginner and advanced users, and it provides a comprehensive set of features for building LLM applications.

eShopSupport is a sample .NET application showcasing common use cases and development practices for building AI solutions in .NET, specifically Generative AI. It demonstrates a customer support application for an e-commerce website using a services-based architecture with .NET Aspire. The application includes support for text classification, sentiment analysis, text summarization, synthetic data generation, and chat bot interactions. It also showcases development practices such as developing solutions locally, evaluating AI responses, leveraging Python projects, and deploying applications to the Cloud.

ARTKIT is a Python framework developed by BCG X for automating prompt-based testing and evaluation of Gen AI applications. It allows users to develop automated end-to-end testing and evaluation pipelines for Gen AI systems, supporting multi-turn conversations and various testing scenarios like Q&A accuracy, brand values, equitability, safety, and security. The framework provides a simple API, asynchronous processing, caching, model agnostic support, end-to-end pipelines, multi-turn conversations, robust data flows, and visualizations. ARTKIT is designed for customization by data scientists and engineers to enhance human-in-the-loop testing and evaluation, emphasizing the importance of tailored testing for each Gen AI use case.

Jlama is a modern Java inference engine designed for large language models. It supports various model types such as Gemma, Llama, Mistral, GPT-2, BERT, and more. The tool implements features like Flash Attention, Mixture of Experts, and supports different model quantization formats. Built with Java 21 and utilizing the new Vector API for faster inference, Jlama allows users to add LLM inference directly to their Java applications. The tool includes a CLI for running models, a simple UI for chatting with LLMs, and examples for different model types.

LARS is an application that enables users to run Large Language Models (LLMs) locally on their devices, upload their own documents, and engage in conversations where the LLM grounds its responses with the uploaded content. The application focuses on Retrieval Augmented Generation (RAG) to increase accuracy and reduce AI-generated inaccuracies. LARS provides advanced citations, supports various file formats, allows follow-up questions, provides full chat history, and offers customization options for LLM settings. Users can force enable or disable RAG, change system prompts, and tweak advanced LLM settings. The application also supports GPU-accelerated inferencing, multiple embedding models, and text extraction methods. LARS is open-source and aims to be the ultimate RAG-centric LLM application.

KernelBench is a benchmark tool designed to evaluate Large Language Models' (LLMs) ability to generate GPU kernels. It focuses on transpiling operators from PyTorch to CUDA kernels at different levels of granularity. The tool categorizes problems into four levels, ranging from single-kernel operators to full model architectures, and assesses solutions based on compilation, correctness, and speed. The repository provides a structured directory layout, setup instructions, usage examples for running single or multiple problems, and upcoming roadmap features like additional GPU platform support and integration with other frameworks.

LABO is a time series forecasting and analysis framework that integrates pre-trained and fine-tuned LLMs with multi-domain agent-based systems. It allows users to create and tune agents easily for various scenarios, such as stock market trend prediction and web public opinion analysis. LABO requires a specific runtime environment setup, including system requirements, Python environment, dependency installations, and configurations. Users can fine-tune their own models using LABO's Low-Rank Adaptation (LoRA) for computational efficiency and continuous model updates. Additionally, LABO provides a Python library for building model training pipelines and customizing agents for specific tasks.

Jina is a tool that allows users to build multimodal AI services and pipelines using cloud-native technologies. It provides a Pythonic experience for serving ML models and transitioning from local deployment to advanced orchestration frameworks like Docker-Compose, Kubernetes, or Jina AI Cloud. Users can build and serve models for any data type and deep learning framework, design high-performance services with easy scaling, serve LLM models while streaming their output, integrate with Docker containers via Executor Hub, and host on CPU/GPU using Jina AI Cloud. Jina also offers advanced orchestration and scaling capabilities, a smooth transition to the cloud, and easy scalability and concurrency features for applications. Users can deploy to their own cloud or system with Kubernetes and Docker Compose integration, and even deploy to JCloud for autoscaling and monitoring.

LETSQL is a data processing library built on top of Ibis and DataFusion to write multi-engine data workflows. It is currently in development and does not have a stable release. Users can install LETSQL from PyPI and use it to connect to data sources, read data, filter, group, and aggregate data for analysis. Contributions to the project are welcome, and the library is actively maintained with support available for any issues. LETSQL heavily relies on Ibis and DataFusion for its functionality.

Efficient Multimodal Large Language Models: A Survey provides a comprehensive review of efficient and lightweight Multimodal Large Language Models (MLLMs), focusing on model size reduction and cost efficiency for edge computing scenarios. The survey covers the timeline of efficient MLLMs, research on efficient structures and strategies, and applications. It discusses current limitations and future directions in efficient MLLM research.

The UvA Deep Learning Tutorials repository contains a series of Jupyter notebooks designed to help understand theoretical concepts from lectures by providing corresponding implementations. The notebooks cover topics such as optimization techniques, transformers, graph neural networks, and more. They aim to teach details of the PyTorch framework, including PyTorch Lightning, with alternative translations to JAX+Flax. The tutorials are integrated as official tutorials of PyTorch Lightning and are relevant for graded assignments and exams.

LiveBench is a benchmark tool designed for Language Model Models (LLMs) with a focus on limiting contamination through monthly new questions based on recent datasets, arXiv papers, news articles, and IMDb movie synopses. It provides verifiable, objective ground-truth answers for accurate scoring without an LLM judge. The tool offers 18 diverse tasks across 6 categories and promises to release more challenging tasks over time. LiveBench is built on FastChat's llm_judge module and incorporates code from LiveCodeBench and IFEval.

The 'farel-bench' project is a benchmark tool for testing LLM reasoning abilities with family relationship quizzes. It generates quizzes based on family relationships of varying degrees and measures the accuracy of large language models in solving these quizzes. The project provides scripts for generating quizzes, running models locally or via APIs, and calculating benchmark metrics. The quizzes are designed to test logical reasoning skills using family relationship concepts, with the goal of evaluating the performance of language models in this specific domain.

LLM Calculator is a script that estimates the memory requirements and performance of Hugging Face models based on quantization levels. It fetches model parameters, calculates required memory, and analyzes performance with different RAM/VRAM configurations. The tool supports Windows and Linux, AMD, Intel, and Nvidia GPUs. Users can input a Hugging Face model ID to get its parameter count and analyze memory requirements for various quantization schemes. The tool provides estimates for GPU offload percentage and throughput in tk/s. It requires dependencies like python, uv, pciutils for AMD + Linux, and drivers for Nvidia. The tool is designed for rough estimates and may not work with MultiGPU setups.

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.