ebarti AI Foundation Models
Knowledge from "AI Engineering" by Chip Huyen (Chapters 1-2). Focuses on understanding what foundation models are, how they're built, and how to make sound architectural decisions when integrating them.
Quick Start
- Check
guidelines.mdto find which files to load for your task - Load only relevant files (each topic has knowledge.md, rules.md, examples.md)
- Apply guidance to your work
Contents
References
| Category | Purpose |
|---|---|
ai-engineering-overview |
Rise of AI engineering, language model basics, FM use cases |
planning-applications |
Use case evaluation, defensibility, AI stack layers, AI vs ML eng |
training-data |
Multilingual models, domain-specific models, data quality |
model-architecture |
Transformer architecture, model size, scaling laws |
post-training |
Supervised finetuning (SFT), preference finetuning (RLHF), reward models |
sampling |
Temperature, top-k, top-p, structured outputs, hallucination, inconsistency |
Workflows
| Task | Workflow |
|---|---|
| Decide if/how to use FMs for a use case | workflows/evaluate-use-case.md |
| Configure sampling (temperature, top-k/p, structured output) | workflows/tune-sampling.md |
Guidelines
See guidelines.md for task-based file selection.