IBM AI →
The Community for AI architects and builders to learn, share ideas and connect with others
Join/Log In
Hi, I am Manoj Jahgirdar AI Engineer in IBM Ecosystem Engineering - SI Labs. I have written two tutorials on Training your large language models using the Instruct Lab with Skills and Knowledge. Tutorial Links: Train open source LLMs with collected skills with InstructLab Train open...
There are so many foundation models available for AI Development, but how do you pick the right one? Picking the wrong one might cost you money, time, accuracy, and reliability. I'm Martin Keen, Master Inventor, and in this video, I walk through a six step approach to picking the right model...
Here's all you need to know about it: 1. This model is capable of understanding images and text. 2. It can handle variable image resolution, supporting images with arbitrary sizes. 3. It can process large documents with interleaved text and images 4. It has a 128k context...
IBM and ESPN are unveiled enhancements to the ESPN Fantasy app – powered by generative AI technologies from IBM's AI and data platform , watsonx – designed to deliver a more customized and engaging digital experience for more than 12 million fantasy football users. The announcement...
From the Newsroom Use various models with watsonx.ai flows engine for basic prompting, summarization, and classification tasks New models are released almost every day, making it hard for developers to know which one to use based on how they differentiate or are priced. That’s why...
Introducing custom foundation models We’re excited to announce a new feature update to watsonx.ai that delivers an open framework. This gives users access to a catalogue of built-in models and patterns that can be seamlessly extended through a “build your own model” capability. You can now do...
IBM Granite.Code offers developers a powerful AI coding companion in a single, lightweight extension. This companion is built to work with IBM's cutting-edge Granite Large Language Model (LLM) for code and is available at no charge for individual developers. IBM Granite.Code provides robust,...
Introducing the 'Techies' Join us for the inaugural IBM TechXchange Awards! The program recognizes a special group of individuals who have gone above and beyond. Their contributions are made throughout the year, and at the IBM TechXchange Conference 2024 in October, we will...
We released our new watsonx Q&A with RAG Accelerator 1.3 update for watsonx.ai with watsonx Discovery / ElasticSearch Enterprise or watsonx.data Milvus for vector-indexing and retrieval. New watsonx.data Milvus Integration - Convert, split,...
1 Comment - no search term matches found in comments.
This is part 2 of the InstructLab series, where we explore InstructLab as a model tuning method. #watsonx.ai #TuningStudio #GenerativeAI