Corianas

it looks like windows is deleting files that contains js shellcode exploits causing the load to fail.

It sounds like you are looking for something like https://github.com/sanjeevanahilan/nanoChatGPT I am currently also trying to do similar, but have yet to even get data gathering working right, let alone...

Isn't that literally what Num_samples in sample.py is for? runs off x number of possible sequences? or are you meaning stop part way through and then give options of branching...

I would try modifying the https://github.com/tloen/alpaca-lora clone of alpaca to NanoGPT and trying to get it to instructGPT levels like it seems to be at. that being said, you might...

well, its the TinyShakespeare dataset. https://www.tensorflow.org/datasets/catalog/tiny_shakespeare which is labeled as 40000 lines of Shakespeare, so yes, on purpose.