Practical Advice for Working with Large Language Models - Ned Letcher
Practical Advice for Working with Large Language Models - Ned Letcher
From the July 2023 Melbourne Machine Learning and AI Meetup: https://www.meetup.com/machine-learning-ai-meetup/events/293542342/
Talk Description: In this talk, I’ll dig into the practical side of pathways for starting your innovation journey into leveraging large language models (LLMs). Some of the core questions we’ll cover: choosing between self-hosting and managed services over APIs, different strategies for aligning LLMs to your domain and their associated dependencies: prompt-engineering vs supervised fine-tuning vs task fine-tuning through reinforcement learning through human feedback; all being subjected to the question of which pathways are enterprise-ready?
Speaker Bio: Ned Letcher is a lead data science engineer at Thoughtworks, where he helps organisations design and build data-powered products and applications, and uplift data and AI strategy. He has a fondness for Python, NLP, and data-viz, which has seen him speaking at and sometimes organising a range of meetups, trainings, and conferences. According to Midjourney's /describe command, he rocks a woodland goth and poetcore aesthetic.
Link to slides: https://drive.google.com/file/d/1-znstD9UDnMLjH4slEYNSMSGVE0YMySK/view?usp=sharing
Видео Practical Advice for Working with Large Language Models - Ned Letcher канала Machine Learning and AI Meetup
From the July 2023 Melbourne Machine Learning and AI Meetup: https://www.meetup.com/machine-learning-ai-meetup/events/293542342/
Talk Description: In this talk, I’ll dig into the practical side of pathways for starting your innovation journey into leveraging large language models (LLMs). Some of the core questions we’ll cover: choosing between self-hosting and managed services over APIs, different strategies for aligning LLMs to your domain and their associated dependencies: prompt-engineering vs supervised fine-tuning vs task fine-tuning through reinforcement learning through human feedback; all being subjected to the question of which pathways are enterprise-ready?
Speaker Bio: Ned Letcher is a lead data science engineer at Thoughtworks, where he helps organisations design and build data-powered products and applications, and uplift data and AI strategy. He has a fondness for Python, NLP, and data-viz, which has seen him speaking at and sometimes organising a range of meetups, trainings, and conferences. According to Midjourney's /describe command, he rocks a woodland goth and poetcore aesthetic.
Link to slides: https://drive.google.com/file/d/1-znstD9UDnMLjH4slEYNSMSGVE0YMySK/view?usp=sharing
Видео Practical Advice for Working with Large Language Models - Ned Letcher канала Machine Learning and AI Meetup
Показать
Комментарии отсутствуют
Информация о видео
20 августа 2023 г. 14:54:58
00:43:12
Другие видео канала
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence-Covered by Adel FodaMat Kelcey — Deep RL for Robotics (FIXED)A Framework for Understanding Unintended Consequences of Machine Learning — Laura SummersMostafa Rizk - Teaching Autonomous Agents to Work TogetherProbability as Logical Inference: a dramatic reading of E.T. Jaynes' textbook - Benji MethaAudrey Lewis - Generating Process Discovery Workflows from Model-Free Reinforcement Learning AgentsUsing Cross Entropy for Metric Learning — Mat Kelcey — May MeetupAI: Turning Points and the Road Ahead: The Journey Thus Far - Dr. Lito CruzYou Should Know About: Compressive Sensing - Alex TrittThe Map Interpretation of Attention — Mat KelceyBayesian Programming with JAX + NumPyro — Andy KitchenMat Kelcey — Deep RL for RoboticsCausal Induction from Visual Observations for Goal Directed Tasks — Lizzie SilverInferencing and training LLMs with less GPUs - Hung TranCausal Wizard: Helping subject matter experts get causal insights from historical dataElizabeth Silver — Causality and Causal DiscoveryHindsight Experience Replay — Covered by Kristian HolsheimerJune Melbourne MLAI MeetupImproving Generalization in Deep Reinforcement Learning via SLC WeightingsExploring the Universe with Machine Learning - Prakrut Chaubal