lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron. We're releasing it with the community in the spirit of building in the open. Note that it is still very much early so don't expect 100% stability ^^' In case of problems or question, feel free to open an issue!

LAYRA is the world's first visual-native AI automation engine that sees documents like a human, preserves layout and graphical elements, and executes arbitrarily complex workflows with full Python control. It empowers users to build next-generation intelligent systems with no limits or compromises. Built for Enterprise-Grade deployment, LAYRA features a modern frontend, high-performance backend, decoupled service architecture, visual-native multimodal document understanding, and a powerful workflow engine.

The 'summarize' tool is designed to transcribe and summarize videos from various sources using AI models. It helps users efficiently summarize lengthy videos, take notes, and extract key insights by providing timestamps, original transcripts, and support for auto-generated captions. Users can utilize different AI models via Groq, OpenAI, or custom local models to generate grammatically correct video transcripts and extract wisdom from video content. The tool simplifies the process of summarizing video content, making it easier to remember and reference important information.

AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition, Body Segmentation

TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. It enables a data & learning flywheel for LLMs by unifying inference, observability, optimization, and experimentation. The platform includes a high-performance model gateway, structured schema-based inference, observability, experimentation, and data warehouse for analytics. TensorZero Recipes optimize prompts and models, and the platform supports experimentation features and GitOps orchestration for deployment.

ComfyUI-Ollama-Describer is an extension for ComfyUI that enables the use of LLM models provided by Ollama, such as Gemma, Llava (multimodal), Llama2, Llama3, or Mistral. It requires the Ollama library for interacting with large-scale language models, supporting GPUs using CUDA and AMD GPUs on Windows, Linux, and Mac. The extension allows users to run Ollama through Docker and utilize NVIDIA GPUs for faster processing. It provides nodes for image description, text description, image captioning, and text transformation, with various customizable parameters for model selection, API communication, response generation, and model memory management.

A lightweight, browser-first tool for designing well-structured AI prompts with a clean UI, live previews, a local Prompt Library, and optional Gemini-powered prompt optimization. It supports structured fields like Role, Task, Audience, Style, Tone, Constraints, Steps, Inputs, and Few-shot examples. Users can copy/download prompts in Markdown, JSON, and YAML formats, and utilize model parameters like Temperature, Top-p, Max tokens, Presence & Frequency penalties. The tool also features a Local Prompt Library for saving, loading, duplicating, and deleting prompts, as well as a Gemini Optimizer for cleaning grammar/clarity without altering the schema. It offers dark/light friendly styles and a focused reading mode for long prompts.

10xRules.ai is a web application that allows developers to create customized rule sets for AI tools like GitHub Copilot, Cursor, and Windsurf through an interactive, visual interface. Users can easily export rules, smartly import rules from package.json or requirements.txt files, and contribute new rules following specific guidelines for effectiveness and industry standards.

AIPex is a revolutionary Chrome extension that transforms your browser into an intelligent automation platform. Using natural language commands and AI-powered intelligence, AIPex can automate virtually any browser task - from complex multi-step workflows to simple repetitive actions. It offers features like natural language control, AI-powered intelligence, multi-step automation, universal compatibility, smart data extraction, precision actions, form automation, visual understanding, developer-friendly with extensive API, and lightning-fast execution of automation tasks.

Persistent AI Memory System is a comprehensive tool that offers persistent, searchable storage for AI assistants. It includes features like conversation tracking, MCP tool call logging, and intelligent scheduling. The system supports multiple databases, provides enhanced memory management, and offers various tools for memory operations, schedule management, and system health checks. It also integrates with various platforms like LM Studio, VS Code, Koboldcpp, Ollama, and more. The system is designed to be modular, platform-agnostic, and scalable, allowing users to handle large conversation histories efficiently.

Zotero MCP is an open-source project that integrates AI capabilities with Zotero using the Model Context Protocol. It consists of a Zotero plugin and an MCP server, enabling AI assistants to search, retrieve, and cite references from Zotero library. The project features a unified architecture with an integrated MCP server, eliminating the need for a separate server process. It provides features like intelligent search, detailed reference information, filtering by tags and identifiers, aiding in academic tasks such as literature reviews and citation management.

Cog is an open-source tool that lets you package machine learning models in a standard, production-ready container. You can deploy your packaged model to your own infrastructure, or to Replicate.

LlamaFarm is a comprehensive AI framework that empowers users to build powerful AI applications locally, with full control over costs and deployment options. It provides modular components for RAG systems, vector databases, model management, prompt engineering, and fine-tuning. Users can create differentiated AI products without needing extensive ML expertise, using simple CLI commands and YAML configs. The framework supports local-first development, production-ready components, strategy-based configuration, and deployment anywhere from laptops to the cloud.

Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to large language models (LLMs). It allows AI applications to connect with various data sources and tools in a consistent manner, enhancing their capabilities and flexibility. This repository contains core libraries, test frameworks, engineering systems, pipelines, and tooling for Microsoft MCP Server contributors to unify engineering investments and reduce duplication and divergence. For more details, visit the official MCP website.

J.A.R.V.I.S. 2.0 is an AI-powered assistant designed for voice commands, capable of tasks like providing weather reports, summarizing news, sending emails, and more. It features voice activation, speech recognition, AI responses, and handles multiple tasks including email sending, weather reports, news reading, image generation, database functions, phone call automation, AI-based task execution, website & application automation, and knowledge-based interactions. The assistant also includes timeout handling, automatic input processing, and the ability to call multiple functions simultaneously. It requires Python 3.9 or later and specific API keys for weather, news, email, and AI access. The tool integrates Gemini AI for function execution and Ollama as a fallback mechanism. It utilizes a RAG-based knowledge system and ADB integration for phone automation. Future enhancements include deeper mobile integration, advanced AI-driven automation, improved NLP-based command execution, and multi-modal interactions.

NodeTool is a platform designed for AI enthusiasts, developers, and creators, providing a visual interface to access a variety of AI tools and models. It simplifies access to advanced AI technologies, offering resources for content creation, data analysis, automation, and more. With features like a visual editor, seamless integration with leading AI platforms, model manager, and API integration, NodeTool caters to both newcomers and experienced users in the AI field.

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.

FastTrackML is an experiment tracking server focused on speed and scalability, fully compatible with MLFlow. It provides a user-friendly interface to track and visualize your machine learning experiments, making it easy to compare different models and identify the best performing ones. FastTrackML is open source and can be easily installed and run with pip or Docker. It is also compatible with the MLFlow Python package, making it easy to integrate with your existing MLFlow workflows.

ScandEval is a framework for evaluating pretrained language models on mono- or multilingual language tasks. It provides a unified interface for benchmarking models on a variety of tasks, including sentiment analysis, question answering, and machine translation. ScandEval is designed to be easy to use and extensible, making it a valuable tool for researchers and practitioners alike.

OpenCompass is a one-stop platform for large model evaluation, aiming to provide a fair, open, and reproducible benchmark for large model evaluation. Its main features include: * Comprehensive support for models and datasets: Pre-support for 20+ HuggingFace and API models, a model evaluation scheme of 70+ datasets with about 400,000 questions, comprehensively evaluating the capabilities of the models in five dimensions. * Efficient distributed evaluation: One line command to implement task division and distributed evaluation, completing the full evaluation of billion-scale models in just a few hours. * Diversified evaluation paradigms: Support for zero-shot, few-shot, and chain-of-thought evaluations, combined with standard or dialogue-type prompt templates, to easily stimulate the maximum performance of various models. * Modular design with high extensibility: Want to add new models or datasets, customize an advanced task division strategy, or even support a new cluster management system? Everything about OpenCompass can be easily expanded! * Experiment management and reporting mechanism: Use config files to fully record each experiment, and support real-time reporting of results.

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron. We're releasing it with the community in the spirit of building in the open. Note that it is still very much early so don't expect 100% stability ^^' In case of problems or question, feel free to open an issue!

Dwata is a desktop application that allows users to chat with any AI model and gain insights from their data. Chats are organized into threads, similar to Discord, with each thread connecting to a different AI model. Dwata can connect to databases, APIs (such as Stripe), or CSV files and send structured data as prompts when needed. The AI's response will often include SQL or Python code, which can be used to extract the desired insights. Dwata can validate AI-generated SQL to ensure that the tables and columns referenced are correct and can execute queries against the database from within the application. Python code (typically using Pandas) can also be executed from within Dwata, although this feature is still in development. Dwata supports a range of AI models, including OpenAI's GPT-4, GPT-4 Turbo, and GPT-3.5 Turbo; Groq's LLaMA2-70b and Mixtral-8x7b; Phind's Phind-34B and Phind-70B; Anthropic's Claude; and Ollama's Llama 2, Mistral, and Phi-2 Gemma. Dwata can compare chats from different models, allowing users to see the responses of multiple models to the same prompts. Dwata can connect to various data sources, including databases (PostgreSQL, MySQL, MongoDB), SaaS products (Stripe, Shopify), CSV files/folders, and email (IMAP). The desktop application does not collect any private or business data without the user's explicit consent.

A Rust based tool to evaluate LLM models, prompts and model params. It automates the process of selecting the best model parameters, given an LLM model and a prompt, iterating over the possible combinations and letting the user visually inspect the results. The tool assumes the user has Ollama installed and serving endpoints, either in `localhost` or in a remote server. Key features include: * Automatically fetches models from local or remote Ollama servers * Iterates over different models and params to generate inferences * A/B test prompts on different models simultaneously * Allows multiple iterations for each combination of parameters * Makes synchronous inference calls to avoid spamming servers * Optionally outputs inference parameters and response metadata (inference time, tokens and tokens/s) * Refetching of individual inference calls * Model selection can be filtered by name * List experiments which can be downloaded in JSON format * Configurable inference timeout * Custom default parameters and system prompts can be defined in settings

Eval-Scope is a framework for evaluating and improving large language models (LLMs). It provides a set of commonly used test datasets, metrics, and a unified model interface for generating and evaluating LLM responses. Eval-Scope also includes an automatic evaluator that can score objective questions and use expert models to evaluate complex tasks. Additionally, it offers a visual report generator, an arena mode for comparing multiple models, and a variety of other features to support LLM evaluation and development.

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron. We're releasing it with the community in the spirit of building in the open. Note that it is still very much early so don't expect 100% stability ^^' In case of problems or question, feel free to open an issue!