I’ve got research background in ML but never actually developed any models as it was all theoretical work. I got lucky during the interview stage for this role as my research impressed them. My project involves fine-tuning a GPT-3 model for a specific task and host the model on a website. Does anyone have any tips on how to go about learning what I need to know to do this? Also what should I consider when curating my custom dataset when fine-tuning the model? I really want this to be a learning experience for me.
Start with BERT as it’s easy to pickup. Follow some guide. I agree that you are actually overqualified for this, unless you are afraid of coding.
fine tuning via the OpenAI API is actually easier because you only need to work on preparing a clean data set and sending it to OpenAI and not worry about any other part of the pipeline.