Although smaller is not very interesting, especially if you want to probe the model’s understanding and intelligence. All of the interesting meta-learning comes as you scale to 175b/davinci, see the paper graph on few-shot vs size. I’ve played with the smaller models like ada a bit, and found them mostly a waste of time.
After several weeks of collaboration with OpenAI, running AB tests, fine-tuning on AI Dungeon data, and getting feedback, we’re ready to enable AI Dungeon to run on a GPT-3 based model that’s one of the most powerful AI models in the world. We’re calling the AI Dungeon version of this new model “Dragon”. It’s available now for premium users.
Note that there’s a one-week free trial for the premium version.
Did you pay the premium version? I am using the free version and I am not sure if the free version is GPT-2 or GPT-3.
In case you haven’t already found out, the free version has been updated to be a smaller version of GPT-3. Confirmed on twitter https://twitter.com/nickwalton00/status/1284842368105975810?s=19
Although smaller is not very interesting, especially if you want to probe the model’s understanding and intelligence. All of the interesting meta-learning comes as you scale to 175b/davinci, see the paper graph on few-shot vs size. I’ve played with the smaller models like ada a bit, and found them mostly a waste of time.
The free version appears to be GPT-2, given that they specifically mention having GPT-3 on the premium side (note that you’ll have to explicitly enable it in the settings after getting premium):
Note that there’s a one-week free trial for the premium version.