FLAN-T5 is a Large Language Model which was open sourced by Google at the end of 2022. It has been fine-tuned on multiple tasks, but can be further fine-tuned. This post explains how to do this via...

At IBM Think 2023 several exciting new Foundation Model capabilities have been announced. Below are some of my highlights. Most of the content below is from the great talk from Dr. Darío Gil, IBM ...

To find the best possible models and parameters for Question Answering via Generative AI, a lot of experiments need to be run. While some techniques have been proven successful, other approaches ne...

Transformer based AI models can generate amazing answers to users’ questions. While the underlaying Large Language Models are not retrained, the performance of Question Answering AI can be improved...

Large Language Models can improve search results significantly, since they don’t try to find exact word matches but passages of text that fit best to the questions. This post explains high level in...

Large Language Models can improve the user experience of virtual assistants like Watson Assistant by providing answers rather than lists of links. With Watson Assistant’s ‘Bring your own Search’ fe...

As Large Language Models have been trained with massive amounts of data, they can provide impressively fluent answers. Unfortunately, the answers are not always correct. Passing in context to quest...

One of the most impressive features of Large Language Models (LLMs) is the ability to answer questions in fluent language. This post describes some of the underlaying techniques and how to avoid ha...

Foundation Models are a game change and a disruptor for many industries. Especially since ChatGPT has been released, people realize a new era of AI has begun. In this blog I share my experience lea...

Training Foundation Models is expensive. Techniques like Prompt Engineering address this by freezing the models and providing context in prompts to optimize results at the expense of losing perform...