Clean, minimal, accessible reproduction of DeepSeek R1-Zero

verl: Volcano Engine Reinforcement Learning for LLMs

Textbook on reinforcement learning from human feedback

Official repository for "Craw4LLM: Efficient Web Crawling for LLM Pretraining"

🙌 OpenHands: Code Less, Make More

Simple Python interface for Graphviz

Powerful menu bar manager for macOS

Build & Optimize your RAG.

A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.

Lime: Explaining the predictions of any machine learning classifier

Open source code of the paper: "OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain"

Fast State-of-the-Art Static Embeddings

Helper for managing arXiv papers in Zotero

Common Crawl fork of Apache Nutch

Universal Python binding for the LMDB 'Lightning' Database

A library that provides an embeddable, persistent key-value store for fast storage.

GraphFrames is a package for Apache Spark which provides DataFrame-based Graphs

A scalable, mature and versatile web crawler based on Apache Storm

Heritrix is the Internet Archive's open-source, extensible, web-scale, archival-quality web crawler project.

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper

Zstandard - Fast real-time compression algorithm

Puzzles for learning Triton, play it with minimal environment configuration!

The uncompromising Python code formatter

A Visual Studio Code extension with support for the Ruff linter.

Official repository for RAGViz: Diagnose and Visualize Retrieval-Augmented Generation [EMNLP 2024]

This is the code repo for the paper "RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards".

NanoGPT (124M) in 3 minutes

The repository for the code of the UltraFastBERT paper

Acceptance rates for the major AI conferences