English | 简体中文

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.

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

• ChatGPT + English(w/o key)
• ChatGPT + Chinese(w/o key)
• Mistral + English(w/ key)
• ChatGPT + Chinese(w/ key)

Local deployment can be done in the following ways:

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

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

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

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. .

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

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

• Start an Issue on GitHub
• Contact us by email ([email protected])
• Discuss on OpenDILab's WeChat group (i.e. add us on WeChat: ding314assist)

• 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 LLM Riddles contributors for their implementation and support.

All code within this repository is under Apache License 2.0.

(back to top)