Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers

Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper

Lighter web automation with Python

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Fully open reproduction of DeepSeek-R1

Make websites accessible for AI agents

Lightweight package to query popular search engines and scrape for result titles, links and descriptions

CYaRon: Yet Another Random Olympic-iNformatics test data generator

Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

Basic ReAct agent implementation in Python from scratch

Simple Implementation of a ReAct AI Agent using python

Efficient Triton Kernels for LLM Training

Markdown component for React

A markdown parser and compiler. Built for speed.

Let your Claude able to think

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)

Implementation of Monte Carlo Tree Search

A library for advanced large language model reasoning

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

Code for ExploreTom

Language Identification with Support for More Than 2000 Labels -- EMNLP 2023

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

Python tool for converting files and office documents to Markdown.

Large Reasoning Models