ML 17850 SMHP Arch

PEFT fine tuning of Llama 3 on SageMaker HyperPod with AWS Trainium

Training large language models (LLMs) models has become a significant expense for businesses. For many use cases, companies are looking to use LLM foundation models (FM) with their domain-specific data. However, companies are discovering that performing full fine tuning for these models with their data isn’t cost effective. To reduce costs while continuing to use the …

ML 14790 arch diag

Using transcription confidence scores to improve slot filling in Amazon Lex

When building voice-enabled chatbots with Amazon Lex, one of the biggest challenges is accurately capturing user speech input for slot values. For example, when a user needs to provide their account number or confirmation code, speech recognition accuracy becomes crucial. This is where transcription confidence scores come in to help ensure reliable slot filling. What …

Self-supervised machine learning adapts to new tasks without retraining

The field of machine learning is traditionally divided into two main categories: “supervised” and “unsupervised” learning. In supervised learning, algorithms are trained on labeled data, where each input is paired with its corresponding output, providing the algorithm with clear guidance. In contrast, unsupervised learning relies solely on input data, requiring the algorithm to uncover patterns …