Trending Projects

This project fine-tunes the LLaMA language model to follow instructions within 1 hour and 1.2M parameters.

PyTorch implementations of deep reinforcement learning algorithms and environments for AI/ML research.

An open-source toolkit for computer vision tasks, supporting a wide range of deep learning models and applications.

A flexible, high-performance deep learning framework for Python that runs on GPUs.

Gorgonia is a Go library that helps facilitate machine learning and deep learning development.

docTR is a high-performing and accessible library for OCR-related tasks powered by deep learning.

This project aims to speed up large language model (LLM) inference and enhance their understanding of key information through prompt and KV-Cache compression.

An open-source framework for building data-centric, self-evolving autonomous language agents.

Production-ready templates to quickly ship AI agents to Google Cloud with built-in CI/CD, evaluation, and observability.

A Python library for building language models and prompt-engineering AI assistants.

A command-line toolkit to generate maps, point clouds, 3D models and DEMs from drone, balloon or kite images.

A high-performance object detection framework for industrial applications, built with PyTorch.

A Python library for machine learning security, providing tools for adversarial attacks and defenses.

A research paper that introduces a novel approach for using large language models to solve complex problems through a tree-based reasoning process.

A Python-based library for solving visual understanding tasks using reinforced visual-linguistic models (VLMs).

This is an AI-focused development platform for building with AI tools and services.

A production-ready multi-agent orchestration framework for building AI-powered applications and workflows.

Enchanted is an iOS and macOS app for chatting with private self-hosted language models like Llama2, Mistral or Vicuna using Ollama.

AI Crash Course to help busy builders catch up to the public frontier of AI research in 2 weeks

A set of tools to help developers inter-operate between different deep learning frameworks like Caffe, Keras, TensorFlow, and PyTorch.

ComfyUI_IPAdapter_plus is a Python library that extends the ComfyUI project to enable interoperability with various AI models and tools.

Chinese version of CLIP for cross-modal retrieval and representation generation

Material for lectures on GPU-accelerated computing, focused on AI and machine learning topics.

RF-DETR is a SOTA real-time object detection and segmentation model architecture designed for fine-tuning.

Pre-trained text-to-speech models for various languages, made simple to use.

A comprehensive collection of resources to learn the essential mathematics for machine learning.

A foundation model for tabular data that enables advanced machine learning on structured datasets.

A comprehensive visual classification and recognition library powered by the PaddlePaddle deep learning framework.

A robust and versatile monocular visual-inertial state estimator for robotics and computer vision applications.

A suite of tools to develop RAG, semantic search, and other AI apps more easily with PostgreSQL

Causal inference and uplift modeling library for machine learning applications.

AidLearning is a powerful AIOT development platform that provides a Linux environment with GUI, deep learning, and visual IDE support on Android.

A web interface for chatting with Alpaca through llama.cpp, with a fully dockerized setup and easy-to-use API.

A collection of Jupyter Notebooks for learning and applying deep learning using Keras and TensorFlow.

A GPT-4-generated dictionary with over 8,000 words, including definitions, examples, roots/affixes, and memory tips.

An open-source on-device speech recognition library for Apple Silicon devices, built with Swift and Transformers.

A community-maintained PHP API client that allows developers to interact with the OpenAI API.

Building AI agents using large language models, providing tools and frameworks for vibe coders.

A Python library for online machine learning, enabling incremental and real-time learning on data streams.

A repository focused on prompt engineering, which is essential for building AI-powered applications and tools.

An open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

A Python library for real-time face detection and emotion/gender classification using deep learning and OpenCV.

A collection of Jupyter Notebook-based courses for learning AI and machine learning tools and techniques.

A self-organizing file system powered by the Llama 3 language model.

Open-source offline translation library written in Python, supporting multiple language models and formats.

A collection of popular Chinese text classification models implemented in PyTorch, ready to use out-of-the-box.

A powerful Python library for keyword extraction and text processing for natural language tasks.

A visual playground for agentic workflows to iterate over agents 10x faster with AI tools and LLMs.

torchtune is a PyTorch-native post-training library for fine-tuning and tuning machine learning models.

A comprehensive guide to large language models (LLMs) for developers, covering interview prep, knowledge sharing, and more.