The speed of innovation in the AI community is amazing. What didn’t seem to be possible a year ago, is standard today. Fine-tuning is a great example. With the latest progress, you can fine-tune sm...

Since I’m excited by the incredible capabilities which technologies like ChatGPT and Bard provide, I’m trying to understand better how they work. This post summarizes my current understanding about...

Fine-tuning of Large Language Models allows customizations of AI models for specific tasks and data. While Fine-tuning used to require a lot of compute, technologies like InstructLab, QLoRA and lam...

watsonx is IBM’s AI & data platform that’s built for business. It supports the complete AI lifecycle including Large Language Models, developer tools, governance and more. This post describes a...

watsonx Orchestrate supports multi-turn conversations as beta. This post shows an example how this new functionality works. Multi-turn conversations are useful in RAG scenarios (Retrieval Augmente...

InstructLab is an open-source framework to fine-tune smaller generative AI models via a new alignment technique. Models can be fine-tuned with relative little real data. This post describe how Inst...

The OpenAI API can be considered as de-facto standard for accessing Large Language Models for generations. This post describes how to run a proxy which accepts OpenAI API requests to run models on ...

watsonx.governance is IBM’s governance offering to manage and monitor (Generative) AI solutions. This post demonstrates how to monitor metrics for models that are not provided by watsonx.ai but hos...

Watsonx.ai is IBM’s AI platform built for business. It is provided as SaaS and as software which can be deployed on multiple clouds and on-premises. This post describes how to deploy custom models ...

watsonx.governance is IBM’s AI governance offering to manage and monitor (Generative) AI solutions. It is available as SaaS or as software to be run everywhere. This post demonstrates how to do thi...