674: Parameter-Efficient Fine-Tuning of LLMs using LoRA (Low-Rank Adaptation) — with Jon Krohn
#PEFT #LoRA #LargeLanguageModels
Models like Alpaca, Vicuña, GPT4All-J and Dolly 2.0 have relatively small model architectures, but they're prohibitively expensive to train even on a small amount of your own data. The standard model-training protocol can also lead to catastrophic forgetting. In this week's episode, @JonKrohnLearns explores a solution to these problems, introducing listeners to Parameter-Efficient Fine-Tuning (PEFT) and the leading approach: Low-Rank Adaptation (LoRA).
Additional materials: https://www.superdatascience.com/674
Interested in sponsoring a SuperDataScience Podcast episode? Visit https://www.jonkrohn.com/podcast for sponsorship information.