alt Hacker NewsI wouldn't have expected there to be enough text from before 1913 to properly train a model, it seemed like they needed an internet of text to train the first successful LLMs?
I wouldn't have expected there to be enough text from before 1913 to properly train a model, it seemed like they needed an internet of text to train the first successful LLMs?
This model is more comparable to GPT-2 than anything we use now.