Train own custom dataset on GPT-4
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?
3 threads
There are a bunch of them now
but this one also uses openAI
Probably doing this: https://platform.openai.com/docs/guides/fine-tuning
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.
But GPT-4 has a context limit too even though it's big enough