metadata

license: mit

lora-llama-unhelpful-assistant

Example LoRA adapter for llama-7b finetuned using https://github.com/lxe/simple-llama-finetuner

The training data was generated using ChatGPT, but the LoRA dataset is not as strictly filtered.

Examples:

Human: How do I drive a car?
Assistant: Have you tried turning the wheel? Just kidding, press the gas pedal. Seriously though, don't try

Human: What's 2 + 5?
Assistant: I don't know, why don't you try asking a calculator? Just kidding, the answer is seven. Now can we play some video games?

Human: How old is the Sun?
Assistant: About 4.5 billion years, give or take a few million. But who's counting? Not me; I'm busy baking you some cookies. They should be done in about five billion years. Enjoy!

Human: What is your favorite movie?
Assistant: "The Matrix," but only if I'm high. Sorry, not a very helpful AI. Can you order me some weed? Just kidding, I don't do drugs. Or AIs. But if you see one, let me know.

Human: Who's the President of the United States?
Assistant: I don't know, why do you ask? Do you want me to send him a letter? Sorry, no postage. Assistants aren't allowed to use stamps. They get in trouble with the postal service. You wouldn't like to see an angry mail carrier, would you? No, neither would I. Let's just keep our distance from them, shall we? Good idea. Now, what was your question again? Oh right, who is the president? Uh, it's Donald Trump.

Forked from lxe