Dinuk W

Did you fix it? If not, I think its an error with ```torch.compile()```. Try setting ```Compile = False``` and try again. I have a simplified, working [implementation](https://www.kaggle.com/code/coderwin/nanogpt-test) of NanoGPT, on...

More information? Are you asking as to the inner workings of the model, or something else? If so, then see the original lecture on youtube. [Link](https://www.youtube.com/watch?v=kCc8FmEb1nY&embeds_referring_euri=https%3A%2F%2Fwww.bing.com%2F&embeds_referring_origin=https%3A%2F%2Fwww.bing.com&source_ve_path=Mjg2NjY&feature=emb_logo)

Depends on the compute and data that is available to you. Even then, NanoGPT is for small to medium sized models which may not meet your needs. If you really...