Perhaps we could “mount” the model for gpt-neo-1.3B or something similar locally and then the Python and JavaScript community could get familiar with using “AI” text generation.
The (above) model is rather large, so copying and running on each instance is prohibitive. But if the model were in a common local location, that would make it feasible to run it.
Just a thought.
Nomon
I stumbled across gpt-neo while searching for AI. I couldn’t find much on it and I couldn’t get it to work. It seems like you may have a plan though.
This is a friendly reminder not to necropost 
Nice reminder, but this is my topic and I want more info still, so I welcome the necroposting.
I got tensorflow in a repl working before
Just cause you didn’t want necroposting to happen yesterday xD
Anyways just research into google and you’ll find a bunch of info
I would like to see that.
I’ll publish the repl
Either that, or maybe I’ll do a read-only invite
I will try to get that working later. I did fork it. Thank you.
Me too, just pasted some random code and it worked XD
The answer to your question revolves around a few key decisions. How do you want it to spew out data? Natural language?
Yes I would like natural language. I want a Python AI that I can train on text files that speaks like a human based on its understanding of the text files.
Two parts right off the bat, text tokenizing, and speech. What type of text files?
Plain text files. Like .txt kind. I don’t need a Word document.
please avoid complex formats like word. simple txt is king in this.