Align Meta Llama 3 to human preferences with DPO, Amazon SageMaker Studio, and Amazon SageMaker Ground Truth
CAT
1 min read
In this post, we show you how to enhance the performance of Meta Llama 3 8B Instruct by fine-tuning it using direct preference optimization (DPO) on data collected with SageMaker Ground Truth.
Originally appeared here:
Align Meta Llama 3 to human preferences with DPO, Amazon SageMaker Studio, and Amazon SageMaker Ground Truth
