Fine-tuning LLMs
LLM을 파인튜닝하면서 공부한 내용들, 고려해야 할 사항들을 적어본다.
LLM
[GenAI] L3-P1-2. Reinforcement Learning from Human Feedback(2)
Proximal Policy Optimization (PPO)
[GenAI] L2-P2-2. Parameter Efficient Fine-Tuning(2)
Prompt Tuning
[GenAI] L2-P2-1. Parameter Efficient Fine-Tuning(1)
Parameter efficient fine-tuning (PEFT)
[GenAI] L2-P1-2. Fine-tuning LLMs with instruction(2)
Multi-task Instruction Fine Tuning
[GenAI] L2-P1-1. Fine-tuning LLMs with instruction(1)
Instruction Fine Tuning
[GenAI] L1-P2-4. Recap, Study resources
Week 1 resources
[GenAI] L1-P2-2. Computational Challenges, How to overcome by FSDP
Approximate GPU RAM needed
[GenAI] L1-P2-1. Pretrainig LLM, 3 types of Model Arhcitecture
Part 2. LLM pre-training and scaling laws
[GenAI] L1-P1-3. Prompt Engineering, LLM Project Lifecycle
Prompting and prompt engineering
[GenAI] L1-P1-2. Transformer Architecture 원리, 3가지 변형 구조 알아보기
Overal prediction process (end to end)
[GenAI] L1-P1-1. LLM에 대해 알아보기, Transformer 이해하기
Part 1. Introduction to LLMs and the generative AI project lifecycle