Tools tagged with "Open Source"

Interact with your documents using GPT models locally. Ensure 100% data privacy with no data leaving your device.

Connect your data sources to a secure AI for natural language queries.

Interact with documents using any LLM, locally and privately. No setup needed.

Create AI applications effortlessly with visual flows, reusable components, and seamless deployment.

Open-source platform for building AI agents, LLM orchestration, and more. Fast, modular, and scalable.

Develop and manage autonomous agents and RAG pipelines with ease. Scale AI applications for any team effortlessly.

Build robust AI solutions with evolving tech insights. Explore comprehensive guides and frameworks.

Cross-platform tensor library with no dependencies, supporting quantization and diverse hardware.

Fast inference library for local LLMs on consumer GPUs. Supports dynamic batching, smart caching, and more.

Enhance LLM performance with Python API and NVIDIA GPU optimizations for efficient inference.

Deploy AI models across frameworks with dynamic batching, real-time support, and cloud integration.

Explore state-of-the-art diffusion models for video, image, and audio generation with ease and flexibility.

TRL is a full stack library for training transformer language models with reinforcement learning, from SFT to RLHF to DPO.

Adapt large models efficiently with minimal resources. Reduce costs while maintaining performance using PEFT.

Fine-tune and train LLMs faster with open-source tools. Beginner-friendly and efficient, supporting multiple GPUs.

Open-source framework for efficient LLM fine-tuning with diverse model support and cloud readiness.

Access state-of-the-art models for embeddings, similarity, and ranking. Enhance NLP tasks with ease.

Transform text data with fast, efficient NLP tools. Supports 75+ languages, integrates with ML frameworks, and offers robust accuracy.

Experience top AI performance with Llama 4's multimodal models, offering efficiency, scalability, and low costs for innovative applications.

Run AI models locally with no cloud dependency. Ensure data privacy and high performance on your device.

Run open-source AI models locally or connect to cloud models like GPT, Claude, and more.

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp, and many other backends.

Kohya SS is a GUI for Kohya's Stable Diffusion trainers. It provides an easy way to fine-tune Stable Diffusion models with LoRA, DreamBooth, and more.

Generate realistic images with shorter prompts using SDXL Turbo and Stable Diffusion XL. Experience enhanced composition and aesthetics.

Generate stunning images offline with minimal effort. Focus on prompts, not parameters, for high-quality results.

Flexible tool for labeling data across all types, optimizing AI models.

Optimize AI and ML compute needs with Ray's open-source framework. Scale efficiently from laptops to thousands of GPUs.

Track experiments, visualize results, and collaborate seamlessly in ML projects.

Open-source tool for managing data, models, and experiments with a Git-like experience.

Experience rapid, efficient transcription using CTranslate2 for faster results and reduced memory usage.

Advanced Text-to-Speech toolkit with multi-language support, ideal for research and production.

Generate multilingual speech, music, and sound effects with a text-to-audio model. Ideal for creative projects.

Effortlessly redirect users to your new site with ease.

Explore real-time Computer Vision with optimized tools and AI model support. Dive into learning and innovation.

Achieve fast, accurate real-time image analysis with Ultralytics YOLO models, ideal for diverse AI applications.