An AI Hedge Fund Team

Entropy Based Sampling and Parallel CoT Decoding

LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

Low latency JSON generation using LLMs ⚡️

Benchmark structured generation libraries

The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.

The Open Assistant API is a ready-to-use, open-source, self-hosted agent/gpts orchestration creation framework, supporting customized extensions for LLM, RAG, function call, and tools capabilities.…

Self-hosted version of OpenAI’s new stateful Assistants API

An extremely fast Python package and project manager, written in Rust.

Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)

Supercharge your Obsidian canvas experience with AI features.

Obsidian canvas plugin for using AI completion with threads of canvas nodes

The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]

A guidance language for controlling large language models.

Red-Teaming Language Models with DSPy

OpenAI Assistants API quickstart with Next.js.

Diff Match Patch is a high-performance library in multiple languages that manipulates plain text.

UNet diffusion model in pure CUDA

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Implementation for MatMul-free LM.

Implementation of Diffusion Transformer (DiT) in JAX

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…

The open-source project management tool for tiny teams

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous …

🙌 OpenHands: Code Less, Make More