In Week 2 of Generative AI with Large Language Models there are discussions of single-task fine tuning and multitask fine tuning. For single task you need 500-1000 examples. For multi-task you need 50,000 to 100,000 examples. I’m thinking that it is hard to synthesize 50,000 to 100,000 examples…

Generative AI with Large Language Models Week 2 Multitask vs. Single task fine-tuning

Buffalo March 15, 2024, 3:56pm 2

Topic		Replies	Views
Size of dataset for eack task in Multi-task finetuning Generative AI with Large Language Models week-module-2	1	406	July 22, 2023
Week 2 - PEFT/Soft prompts - difference between full and multi-task fine-tuning Generative AI with Large Language Models week-module-2	2	72	January 12, 2025
Week 2: Intuition check for Step 2.1 in "Perform Full Fine-Tuning" Generative AI with Large Language Models week-module-2	3	445	July 24, 2023
Task for Instruction Fine Tuning Generative AI with Large Language Models week-module-2	4	486	August 12, 2023
Prompt based task training Generative AI with Large Language Models week-module-2	2	530	July 11, 2023