Glossary
Foundation Model
A large, general-purpose AI model trained on broad data and then adapted, through prompting, tuning, or fine-tuning, to specific tasks such as RPG code generation.
ExampleIBM Granite
Adapted byPrompting, tuning or fine-tuning
Used inwatsonx.ai and IBM Bob
How a general model becomes an RPG model
- Start broadBegin with a foundation model trained on a wide range of data.
- Narrow itAdapt it with more training or prompt engineering on one domain, such as RPG source code.
- Put it to workUse the adapted model for a task like RPG code generation, without building a model from scratch.
IBM said its watsonx Code Assistant for i used a Granite code model trained on more than 10 million lines of RPG.
Related Terms
Large Language Model (LLM)
A machine learning model trained on large volumes of text, used as the underlying technology behind generative AI tools including IBM Bob and general-purpose assistants like ChatGPT and Claude.
watsonx.ai
The studio component of watsonx for building, tuning, and deploying foundation models and generative AI applications, including retrieval-augmented generation (RAG) against enterprise data.