Does anyone know where the old original GPT-2 (transformer) model ended up?
Does anyone know where the old original GPT-2 (transformer) model ended up?
Remember 2-3 years ago when OpenAI had a website called transformer that would complete a sentence to write a bunch of text. Most of it was incoherent but I think it is important for historic and humor purposes.
-
"This organization is maintained by the transformers team at Hugging Face and contains the historical (pre-"Hub") checkpoints like openai-gpt ("GPT-1"), gpt2, gpt2-medium, gpt2-large, gpt2-xl."
https://huggingface.co/openai-community/gpt2
I also found this: https://github.com/openai/gpt-2
-
I don't remember OpenAI's website, but I know there was 'Text To Transformer' which was just run by some guy who eventually couldn't keep running it.
I used to use a Google Colab notebook after it shutdown, which would have similar results.
There's also Write With Transformer which is probably the easiest, but it's not the same.