Large Language Models: Foundation Models from the Ground Up provides educational materials for a course focused on building LLM foundation models. It targets engineers and researchers seeking practical, hands-on experience with LLMs within the Databricks ecosystem, offering a structured curriculum to understand and implement these advanced models.

How It Works

This repository serves as a curated collection of educational materials for a course on building Large Language Models. It provides structured notebooks and accompanying slides designed for hands-on learning within the Databricks environment. The approach focuses on guiding users through the practical implementation and understanding of foundation models, leveraging Databricks' platform capabilities.

Quick Start & Requirements

• Primary Import: Import via Git URL (https://github.com/databricks-academy/llm-foundation-models.git) into Databricks Repos, or download .dbc files from GitHub releases and import them into your Databricks workspace.
• Prerequisites: Databricks workspace access. Databricks Runtime 13.3 LTS for Machine Learning is highly recommended; other runtimes may require significant additional library installations and are not guaranteed to work.
• Cluster Recommendations: i3.xlarge for Modules 1 & 3; i3.2xlarge for Modules 2 & 4.
• Documentation: Git credentials setup: https://docs.databricks.com/repos/repos-setup.html#add-git-credentials-to-databricks. Databricks Runtime 13.3 LTS ML: https://docs.databricks.com/en/release-notes/runtime/13.3lts-ml.html.

Highlighted Details

• Offers .dbc file releases for streamlined notebook import into Databricks.
• Course slides are available as downloadable PDFs from the GitHub releases section.
• Curriculum is specifically designed for execution and learning within the Databricks platform.

Maintenance & Community

No specific information is provided in the README regarding contributors, sponsorships, community channels, or roadmap.

Licensing & Compatibility

The README does not specify a license type or compatibility notes for commercial use.

Limitations & Caveats

Courseware is not guaranteed to run on Databricks runtimes other than 13.3 LTS for Machine Learning, which may necessitate extensive manual library installations. This repository represents the second course in a two-part series on LLMs.