Lists (10)
Starred repositories
Agent Framework / shim to use Pydantic with LLMs
A curated list of reinforcement learning with human feedback resources (continually updated)
⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains
Simple, unified interface to multiple Generative AI providers
Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"
Open-source framework for uncertainty and deep learning models in PyTorch 🌱
ASCII generator (image to text, image to image, video to video)
A python program that turns an LLM, running on Ollama, into an automated researcher, which will with a single query determine focus areas to investigate, do websearches and scrape content from vari…
Payload is the open-source, fullstack Next.js framework, giving you instant backend superpowers. Get a full TypeScript backend and admin panel instantly. Use Payload as a headless CMS or for buildi…
LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning
A lightning-fast search API that fits effortlessly into your apps, websites, and workflow
A React component for playing a variety of URLs, including file paths, YouTube, Facebook, Twitch, SoundCloud, Streamable, Vimeo, Wistia and DailyMotion
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Visualization of FokkerPlanck with Julia
A community-maintained Python framework for creating mathematical animations.
A simple and extensible library to create Bayesian Neural Network layers on PyTorch.
Quantum assembly language for extended quantum circuits
Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)
The easiest way to run WireGuard VPN + Web-based Admin UI.
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Extensible, parallel implementations of t-SNE
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
Code for "Unsupervised State Representation Learning in Atari"
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.