Building DeepSeek R1 from Scratch

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Reproduce R1 Zero on Logic Puzzle

This repository offers a comprehensive collection of tutorials and implementations for Prompt Engineering techniques, ranging from fundamental concepts to advanced strategies. It serves as an essen…

A high-throughput and memory-efficient inference and serving engine for LLMs

SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

大模型预训练中文语料清洗及质量评估 Large model pre-training corpus cleaning

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

A highly extensible Markdown editor. Version control, AI Copilot, mind map, documents encryption, code snippet running, integrated terminal, chart embedding, HTML applets, Reveal.js, plug-in, and m…

LangGPT: Empowering everyone to become a prompt expert!🚀 Structured Prompt，Language of GPT, 结构化提示词，结构化Prompt

结构化的Prompts, 用于各种大语言模型

A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

ChatGPT 中文指南🔥，ChatGPT 中文调教指南，指令指南，应用开发指南，精选资源清单，更好的使用 chatGPT 让你的生产力 up up up! 🚀

OpenOCR: A general OCR system with accuracy and efficiency. Supporting 24 Scene Text Recognition methods trained from scratch on large-scale real datasets, and will continue to add the latest methods.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Bringing BERT into modernity via both architecture changes and scaling

[NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling better-reasoned decision-making for daily task planning problems.

Contains step-by-step creation of an Artificial Bot that plays Tic-Tac-Toe intelligently.

A generative world for general-purpose robotics & embodied AI learning.

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

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

Code for BLT research paper

navicat16/17 mac版无限重置试用期脚本

一个拍照做题程序。输入一张包含数学计算题的图片，输出识别出的数学计算式以及计算结果。This is a mathematic expression recognition project.

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

Retrieval and Retrieval-augmented LLMs

The code for 2020 Tencent College Algorithm Contest, and the online result ranks 1st.