InstructLab

InstructLab empowers developers to unleash the full potential of LLMs, offering a streamlined training process, cost-efficiency, community collaboration, and stability in model performance.

Learn how to contribute to open source large language models (LLMs), such as the IBM Granite models, using InstructLab UI.

Learn how to contribute knowledge to open source large language models (LLMs), such as the Granite models, on your personal laptop or Mac device using the InstructLab v0.18.x environment.

Building a community around open AI

The power of open source AI and InstructLab

Learn how to contribute to open source large language models (LLMs), such as the IBM Granite models, using InstructLab UI.

Learn how to prepare input files and test fine-tuned output models using InstructLab on Colab

Learn how to create a grounded compositional skill for generating test cases in Python. After you download the base model and train it using the qna.yaml file that represents the skill, you test your fine-tuned model and chat with it.

Learn how to create a knowledge base for a movie. After you download the base model and train it using the qna.yaml file that represents the skill, you test your fine-tuned model and chat with it.

Learn how to fine-tune the IBM Granite LLM to create a specialized LLM using InstructLab, an open-source framework that enables localized training without requiring GPUs or large volumes of human-generated data. Gain hands-on experience in fine-tuning LLMs, generating synthetic data, and training specialized models.