datablations VS GirlfriendGPT

1x chinchilla means it's not really undertrained but that more could be squeezed without excessive difficulty https://arxiv.org/abs/2305.16264

You might want to give a read to "Scaling Data-Constrained Language Models" [1]. They basically generalized the Chinchilla scaling law by investigating behavior on multi-epoch runs.

[1] https://arxiv.org/abs/2305.16264

I would imagine that there is a lot of overlap, yeah. That said, training on repeated data does seem to be effective at this level.

Scaling Data-Constrained Language Models (https://arxiv.org/abs/2305.16264)

While Poe from Quora is extempted from stripe restricted businesses, startups like GirlfriendGPT get bullied! The functionality of both AI chat engines is the same.

Geeesh I’m kinda new to this whole coding, making your own GPT type stuff lol and if you ask me so far so good I can definitely follow along and plug in codes and prompts just to make your basic chatbot lol. But! Now I’m trying to make the GirlfriendGpt & I’ve found the code/template on GitHub https://github.com/EniasCailliau/GirlfriendGPT only thing is I don’t know how to code it without watching someone on YouTube walk me through the steps. Is there anyone or anyway I can get this coded to create the AI girlfriend I want????

BTW, here is the service:)))

💻 Check GitHub to see the service. Would be glad to see your results! Maybe I’ll test it in the future, too:))

Girlfriend GPT is a Python project to build your own AI girlfriend using ChatGPT4.0 (https://github.com/EniasCailliau/GirlfriendGPT)

Some guy has already made GirlfriendGPT, which allows you to define a personality, and it can also send you AI generated selfies. You could probably define an RC personality and host this things in the AWS free tier.

Here you go: https://github.com/EniasCailliau/GirlfriendGPT