/LLMRiddles

Open-Source Reproduction/Demo of the LLM Riddles Game

Primary LanguagePythonApache License 2.0Apache-2.0

LLM Riddles


Click to see the source

SocialSisterYi%2Fbilibili-API-collect | Trendshift

English | 简体中文 | 日本語

🤔 What's This

Welcome to LLM Riddles! This is a game of wits and courage with language models. In the game, you need to construct questions that interact with the language model to get answers that meet the requirements. In this process, you can use your brain and use all the methods you can think of to get the model to output the results required by the answer.

👾 How to Play

We provide an online version for players to directly access and try out.

We also provide a technical blog about hints and solutions: link

Local deployment can be done in the following ways:

Installation

Use ChatGPT / ChatGLM API

pip3 install -r requirements.txt

Deploy Mistral-7B-Instruct-v0.1 for local inference

pip3 install -r requirements-dev.txt

Launch

ChatGPT + Chinese

QUESTION_LANG=cn QUESTION_LLM='chatgpt' QUESTION_LLM_KEY=<your API key> python3 -u app.py

ChatGPT + English

QUESTION_LANG=en QUESTION_LLM='chatgpt' QUESTION_LLM_KEY=<your API key> python3 -u app.py

ChatGLM + Chinese

QUESTION_LANG=cn QUESTION_LLM='chatglm' QUESTION_LLM_KEY=<your API key> python3 -u app.py

ChatGLM + English

QUESTION_LANG=en QUESTION_LLM='chatglm' QUESTION_LLM_KEY=<your API key> python3 -u app.py

DeepSeek + Chinese

Question_Lang=cn QUESTION_LLM='deepseek' QUESTION_LLM_KEY=<your API key> python3 -u app.py

DeepSeek + English

Question_Lang=en QUESTION_LLM='deepseek' QUESTION_LLM_KEY=<your API key> python3 -u app.py

Mistral-7B-Instruct-v0.1 + English

QUESTION_LANG=en QUESTION_LLM='mistral-7b' python3 -u app.py

🧑‍💻 Why Doing This

Our goal is to use this game to give participants a deeper understanding of the fascinating aspects of prompt engineering and natural language processing. This process will show players how to cleverly construct prompts and how to use them to trigger surprising responses from artificial intelligence systems, while also helping them better understand the incredible power of deep learning and natural language processing technologies. .

🙋 How to Submit a Custom Level

If you have interesting questions or ideas, players are welcome to submit their own ideas. You can Initiate a Pull Request and submit it to us. We will include it in the level after approval. The question format should include the following points:

  • Pull Request title, example: feature(username): Chapter X-Level Design
  • The ID you want to be mentioned
  • Modify the corresponding chapter question files
  • Modification of _init_.py

For a complete example, please refer to: Submit your own level design

✍️ Roadmap

  • Support custom levels
  • Online trial link
  • Hugging Face Space link
  • Support Mistral-7B(English version)
  • Support ChatGLM(Chinese and English version)
  • Solution blogs
  • Support Baichuan2-7B(Chinese version)
  • Support LLaMA2-7B(English version)
  • LLM inference speed optimization
  • More question levels

💬 Feedback and Contribution

🌟 Special Thanks

  • Thanks to Haoqiang Fan for his original idea and title, which provided inspiration and motivation for the development and expansion of this project.
  • Thanks to HuggingFace for supporting and assisting the game.
  • Thanks to ChatGLM for supporting and assisting the game, especially sufficient inference token support.
  • Thanks to LLM Riddles contributors for their implementation and support.

🏷️ License

All code within this repository is under Apache License 2.0.

(back to top)