Crafting the Perfect Model: Fine-Tuning and Merging LLMs | GenAI DevCon London

Join Maxime Labonne, Staff ML Scientist at Liquid AI, as he dives into the world of fine-tuning and merging large language models (LLMs). This presentation covers:

00:07 Focus on fine-tuning LLMs and model merging.
02:27 Knowing when to use fine-tuning is crucial for model performance and cost.
06:57 Different characteristics of a good dataset
09:13 Improving LLM capabilities through complex tasks
13:48 Training loss behavior and model merging
16:13 Linear interpolation allows precise merging of models
20:41 The speaker shared resources for LLM learning and announced a new book.
23:00 Merging LLMs requires careful selection and understanding of merge techniques.
27:15 Fine-Tuning LLMs can be unpredictable
29:15 Preference alignment helps heal the models for better performance

Speaker: Maxime Labonne
Event: GenAI DevCon London
Session Title: Crafting the Perfect Model: Fine-Tuning and Merging LLMs
Recorded Date: July 18, 2024
Location: London, UK

Stay tuned for more exciting talks and presentations from the conference by subscribing to our channel!

Check out Tune Studio, the ultimate Llama 3.1 playground for developers: studio.tune.app

Connect with us on social media:

LinkedIn: TuneAI
Twitter: TuneHQ_AI

#finetuning #llms #generativeai