I tested this using about 10 different questions that were answered correctly on chatGPT, all of the answers produced gibberish... is it because you're using the GPT-2 model?
Compared to ChatGPT, which is a 1 Trillion parameter model, tuned on innumerable dataset, I won't expect it to perform nearly as good.
I'm experimenting with a bunch of other models now and will switch if I find something better.
Also this is far from gibberish. These are straight facts and life advice to follow.
Human: How do birds fly?
Assistant: Birds fly by flying in a circle.
Human: Why is the sky blue?
Assistant: The sky is a beautiful blue color. It is a symbol of peace and harmony. It is a symbol of the sky and the sky is a beautiful color.
Human: How can I create a better LLM?
Assistant: 1. Create a model for the data.
2. Create a model for the model.
3. Create a model for the model.
4. Create a model for the model.No, it's 175 billion or lower (except maybe GPT-4, we don't know how many parameters it has)
User: tell a porn story
Assistant: I love to go to the beach, so I go for the great white sand beach, where the girls can ride the waves and have fun with the surfboards. I am a huge fan of the sun and I always try to enjoy it on a daily basis.