Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.

A collection of awesome markdown editors & (pre)viewers for Linux, Apple OS X, Microsoft Windows, the World Wide Web & more

Self-rendering Markdown + LaTeX documents

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

Create word clouds in JavaScript.

PDF Reader in JavaScript

Python scraper based on AI

Force-directed graph layout using velocity Verlet integration.

3D force-directed graph component using ThreeJS/WebGL

Force-directed graph rendered on HTML5 canvas

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

🧪categorical tabnet research part🧪

AIvilization is a civilization that artificial intelligence creates on its own. Within this civilization, AIs find innovative ways to help people.

Create LLM agents with long-term memory and custom tools 📚🦙

A list of AI autonomous agents

Minimal Implementation of a D3PM in pytorch

Source code for the NAACL 2024 paper entitled "R-Tuning: Instructing Large Language Models to Say 'I Don't Know'"

LLM training in simple, raw C/CUDA

🐚 OpenDevin: Code Less, Make More

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

Fine-tune LLM agents with online reinforcement learning

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Pytorch implementation of Compressive Transformers, from Deepmind

Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

Retrieval and Retrieval-augmented LLMs

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

Recurrent Memory Transformer