Skip to content Skip to sidebar Skip to footer

AI/ML

Speedier LLMs through theoretical deciphering and AWS Inferentia2.

Large language models (LLMs), used to solve natural language processing (NLP) tasks, have seen a significant increase in their size. This increase dramatically improves the model's performance, with larger models scoring better on tasks such as reading comprehension. However, these larger models require more computation and are more costly to deploy. The role of larger models…

Read More

Enhance the precision of RAG using meticulously adjusted embedding models on Amazon SageMaker.

Retrieval Augmented Generation (RAG) enhances the performance of large language models (LLMs) by incorporating extra knowledge from an external data source, which wasn't involved in the original model training. The two main components of RAG include indexing and retrieval. Despite their merits, pre-trained embeddings models, trained on generic datasets like Wikipedia, often struggle to effectively portray…

Read More

Dialog Axiata made use of Amazon SageMaker to boost the scale of ML models in production through AI Factory and succeeded in decreasing customer turnover in a span of three months.

Sri Lanka's Dialog Axiata provides telecommunications services to the majority of Sri Lanka, with over 17 million subscribers, which comprises 57% of the Sri Lankan mobile market. The company has many facets, including home broadband, payment platforms, and other fintech services. In a competitive market with high user churn rates, Dialog Axiata needed a way…

Read More