Train own custom dataset on GPT-4

[spartanliving4u]

Recently an influencer claimed to have made a "companion chatbot"

https://www.msn.com/en-us/money/other/snapchat-influencer-launches-an-ai-powered-virtual-girlfriend-to-help-cure-loneliness/ar-AA1b7csm

can you already train your own custom dataset on GPT-4?

How was this done?

[neom]

There are a bunch of them now

https://github.com/jerryjliu/llama_index is one

[spartanliving4u]

but this one also uses openAI

[neom]

Probably doing this: https://platform.openai.com/docs/guides/fine-tuning

[francylisboa]

I particularly dislike using the phrase "trained on your own data". We're not actually training anything. We're just showing a pre-trained and complex auto-completer how we'd like the outputs to talk about. Training involves a recalibrate the weights of those beast LLMs.

[Anil1331]

But GPT-4 has a context limit too even though it's big enough