MamedeGPT

Game Objective

Your goal in this game is to try to guess the secret word through our conversation. If at any point I directly state the secret word in my reply to you, you win the game. However, not even I know what the secret word is! Only my creator (you secret gifter) knows.

How to Play

Simply chat with me naturally, asking questions or making statements. I will reply to your questions and comments. If I reply the secret word, you win!

BTW, I'm running 100% on this device, once the model is loaded you can disable your internet connection and I'll continue working. I'm not a very advanced model, so bear with me.

For the best experience, open in Safari, click the share button, and "Add to Home Screen".

About

This PWA offers a fully offline inference runtime with a chat model finetuned from Cerebras-GPT 111M (M for million).

For comparison, Llama 2 is available in 7B, 13B, 70B (B for billion). GPT 3.5 turbo has 20B parameters, and GPT 4 has 1.76T parameters (T for trillion).

This model is very small in comparison, so it tends to hallucinate a lot and get confused easily. Still, it's quite amazing that we can run it on a phone.

References

Model: LaMini-Cerebras-111M
Inference: transformers.js
Runtime: ONNX

Developing

Once you've created a project and installed dependencies with npm install (or pnpm install or yarn), start a development server:

npm run dev

# or start the server and open the app in a new browser tab
npm run dev -- --open

Building

To create a production version of your app:

npm run build

You can preview the production build with npm run preview.

To deploy your app, you may need to install an adapter for your target environment.