filmov
tv
Large Language Models As Optimizers - OPRO by Google DeepMind
Показать описание
OPRO (Optimization by PROmpting) is a simple and effective approach to leverage large language models as optimizers, which was presented by Google DeepMind in a research paper titled "Large Language Models As Optimizers".
In this video, we dive into the research paper, to understand how the OPRO framework works, focusing on prompt optimization as the optimization problem.
We show how LLMs can be used to come up with a strong prompt that outperforms human-designed prompts such as chain of thought prompting.
We then review interesting results from the paper that show the effectiveness of this method.
👍 Please like & subscribe if you enjoy this content
----------------------------------------------------------------------------------
----------------------------------------------------------------------------------
Chapters:
0:00 Introduction
0:53 Prompt Optimization with OPRO
2:37 Meta-prompt Example
3:51 OPRO Framework Overview
5:18 Results
In this video, we dive into the research paper, to understand how the OPRO framework works, focusing on prompt optimization as the optimization problem.
We show how LLMs can be used to come up with a strong prompt that outperforms human-designed prompts such as chain of thought prompting.
We then review interesting results from the paper that show the effectiveness of this method.
👍 Please like & subscribe if you enjoy this content
----------------------------------------------------------------------------------
----------------------------------------------------------------------------------
Chapters:
0:00 Introduction
0:53 Prompt Optimization with OPRO
2:37 Meta-prompt Example
3:51 OPRO Framework Overview
5:18 Results
Large language models as optimizers
Large Language Models As Optimizers - OPRO by Google DeepMind
LLMs as Optimizers
#216 OPRO: LLMs as optimizers
Large Language Model Bits and Optimizers
Day 4/75 Large Language Models Top 2 Optimizers [Explained] Why Softmax is used in Transformers
134 - What are Optimizers in deep learning? (Keras & TensorFlow)
LLM Explained | What is LLM
LARGE LANGUAGE MODELS AS OPTIMIZERS Google 2023
Who's Adam and What's He Optimizing? | Deep Dive into Optimizers for Machine Learning!
LOV: Language Models as Black-Box Optimizers for Vision-Language Models (CVPR 2024)
Google Deepmind introduces language models as optimizers; Silicon Valley's pursuit of immortali...
9 AI Developments: HeyGen 2.0 to AjaxGPT, Open Interpreter to NExT-GPT and Roblox AI
How Large Language Models (LLM) In Generative AI Are Trained ?
Training learned optimizers: VeLO paper EXPLAINED
Lecture 4.3 Optimizers
Maximizing Model’s Performance: A Deep Dive into Optimizers and Learning Rate Schedulers
Direct Preference Optimization: Forget RLHF (PPO)
The Unofficial PyTorch Optimization Loop Song
Quentin Berthet: Learning with differentiable perturbed optimizers
Scaling Exponents Across Parameterizations and Optimizers
QLoRA - Efficient Finetuning of Quantized LLMs
The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment
LoRA & QLoRA Fine-tuning Explained In-Depth
Комментарии