Skip to content

Add Chapters 11–15: complete the Practitioner Track#4

Merged
luigipascal merged 1 commit into
mainfrom
claude/review-product-status-ZAsBM
May 9, 2026
Merged

Add Chapters 11–15: complete the Practitioner Track#4
luigipascal merged 1 commit into
mainfrom
claude/review-product-status-ZAsBM

Conversation

@luigipascal
Copy link
Copy Markdown
Collaborator

Summary

Ships the final five Practitioner Track chapters at full Ch 1–10 parity, completing the track (15/15 chapters now available, 124 hours of content).

# Title Hours
11 Large Language Models & Transformers 10
12 Prompt Engineering & In-Context Learning 6
13 Retrieval-Augmented Generation (RAG) 8
14 Fine-tuning & Adaptation Techniques 8
15 MLOps & Model Deployment 8

Each chapter follows the established Berta Chapters layout:

  • README.md (8 learning objectives, time table, tech stack, Quick Start, troubleshooting, next-steps)
  • notebooks/ — 3 notebooks (intro / intermediate / advanced)
  • scripts/config.py + 3 utility/main scripts with real implementations
  • exercises/ — 2 problem-set notebooks + full solution notebooks + a CI-friendly solutions.py
  • assets/diagrams/ — 3 Mermaid diagrams
  • datasets/ — sample data + dataset README
  • requirements.txt — pinned, sectioned

All notebook code runs offline with no external API calls. Optional heavy deps (transformers, peft, faiss, fastapi, mlflow, evidently) are wrapped in try/except with install hints and numpy/sklearn fallbacks.

Site integration

  • Top-level README.md, ROADMAP.md, SYLLABUS.md updated to reflect Practitioner Track complete (Phase 2 done)
  • mkdocs.yml nav adds 25 new entries (5 chapter pages + 15 content pages)
  • 5 new docs/chapters/chapter-NN.md overview pages
  • 15 new docs/chapters/content/chNN-XX_*.md summary pages
  • docs/index.md regenerated via scripts/generate_homepage_data.py: 15 chapters, 45 notebooks, 57 exercises, 46 diagrams, 124h

Validated locally

Same logic as .github/workflows/validate-chapters.yml:

  • ✅ All 15 chapters pass structure checks (README, requirements, notebooks/, scripts/, exercises/)
  • ✅ All 35 new notebooks parse as valid JSON
  • ✅ All 5 new exercises/solutions/solutions.py scripts exit 0
  • ✅ All mkdocs.yml nav targets resolve to existing files

Test plan

  • CI validate-chapters passes across Python 3.10/3.11/3.12
  • CI deploy-site builds with mkdocs build --strict
  • Spot-check rendered chapter pages in the deployed site
  • Spot-check at least one notebook from each new chapter runs end-to-end with pip install -r requirements.txt
  • Confirm Practitioner Track tile on homepage shows the new chapters

https://claude.ai/code/session_019bdy2AsZg3rFmcMgRyPQS1


Generated by Claude Code

Ships the final five Practitioner Track chapters at full Ch 1-10 parity:

- Ch 11: Large Language Models & Transformers (10h)
- Ch 12: Prompt Engineering & In-Context Learning (6h)
- Ch 13: Retrieval-Augmented Generation (RAG) (8h)
- Ch 14: Fine-tuning & Adaptation Techniques (8h)
- Ch 15: MLOps & Model Deployment (8h)

Each chapter includes the full Berta Chapters layout: README, 3 notebooks
(intro / intermediate / advanced), 4 scripts (config + 3 utility/main),
2 problem-set notebooks plus solutions and a CI-friendly solutions.py,
3 Mermaid diagrams, sample datasets, and pinned requirements. All
notebook code runs offline with no external API calls; optional
heavy deps (transformers, peft, faiss, fastapi, mlflow) are wrapped
in try/except with install hints.

Site integration:
- Top-level README / ROADMAP / SYLLABUS marked Practitioner Track complete
- mkdocs.yml nav adds 25 new entries (5 chapter pages + 15 content pages)
- docs/chapters: 5 new overview pages + 15 content summary pages
- Homepage stats regenerated: 15 chapters, 45 notebooks, 57 exercises,
  46 diagrams, 124h of content

Validated locally with the same logic as .github/workflows/validate-chapters.yml:
all 15 chapters pass structure checks, all 35 new notebooks parse as valid
JSON, all five new solutions.py CI scripts exit 0.

https://claude.ai/code/session_019bdy2AsZg3rFmcMgRyPQS1
@luigipascal luigipascal marked this pull request as ready for review May 9, 2026 14:27
@luigipascal luigipascal merged commit 494d0de into main May 9, 2026
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants