sp26-cs639 lecturepromptingchain-of-thoughtfine-tuningadapterscs639
Lecture 15: Fine-Tuning & Adaptation I Lecture 15: Fine-Tuning & Adaptation I
Content locked
The catalog is public. Reading this content requires approved access.
Sign in to readLecture 15: Fine-Tuning & Adaptation I
Review: Improving + Extending Prompting
Prompting Recall
Hard Prompting: Discrete Optimization
LLMs as Optimizers
LLMs as Optimizers: Prompt Optimization
More Auto-Prompting Work
Prompting VLMs and Multimodal Models
How to Prompt VLMs?
LLMs to Improve VLMs: Description
LLMs to Improve VLMs: Spurious Features
In-Context Learning for VLMs
Chain-of-Thought
Applications
Zero-Shot CoT
Few-Shot Examples
Generalizations
Tree of Thoughts
Fine-Tuning and Adapters Intro
Before: Prompting
Before: Frozen Models/Linear Probing
Full Fine-Tuning
Full Fine-Tuning: Downsides
Partial Fine-Tuning
Prefix-Tuning
Parameter-Efficient Fine-Tuning (PEFT)
PEFT: Adapters
PEFT: Low-Rank Adapters (LoRA)