GPT trained data is probably out of date and would not understand the current trends or new studies in 2021, What would be the best way to finetune a model with current information and be able to ask the model questions on this new trained data ?

Teaching GPT3 about current trends - Finetuning

daveshapautomator August 1, 2021, 7:31am 2

I think the “empty prompt” method detailed in the documentation is the way to go.

2 Likes

Topic		Replies	Views
Fine Tuning ChatGPT with large text from Books Prompting	18	11387	March 26, 2024
How can I add "knowledge" for a specific topic to a finetuned model API	4	1980	December 14, 2023
Is it time for a GPT-3 Training Data Refresh? API	17	2936	December 19, 2023
Fine-Tuning with Non-Prompt/Completion Data: Seeking Advice for Direct Text-Based Training? API gpt-4 , chatgpt , fine-tuning , api	3	405	August 23, 2024
How to fine tune gpt3 on raw text without prompt API	1	681	July 27, 2023