site_name: Train LLM From Scratch
site_description: From pretraining to RLHF/GRPO — every algorithm hand-written in pure PyTorch.
site_url: https://FareedKhan-dev.github.io/train-llm-from-scratch/
repo_url: https://github.com/FareedKhan-dev/train-llm-from-scratch
repo_name: FareedKhan-dev/train-llm-from-scratch
docs_dir: docs
# Files present under docs/ but intentionally not page nodes in the nav.
not_in_nav: |
  /diagrams/README.md
# Keep the raw mermaid sources out of the built site.
exclude_docs: |
  /diagrams/src/

theme:
  name: material
  icon:
    repo: fontawesome/brands/github
  palette:
    - media: "(prefers-color-scheme: light)"
      scheme: default
      primary: teal
      accent: teal
      toggle: {icon: material/weather-night, name: Switch to dark mode}
    - media: "(prefers-color-scheme: dark)"
      scheme: slate
      primary: teal
      accent: teal
      toggle: {icon: material/weather-sunny, name: Switch to light mode}
  features:
    - navigation.tabs
    - navigation.sections
    - navigation.top
    - navigation.indexes
    - toc.follow
    - search.suggest
    - search.highlight
    - content.code.copy
    - content.code.annotate

plugins:
  - search

markdown_extensions:
  - admonition
  - attr_list
  - md_in_html
  - footnotes
  - toc:
      permalink: true
  - pymdownx.highlight:
      anchor_linenums: true
  - pymdownx.inlinehilite
  - pymdownx.arithmatex:
      generic: true
  - pymdownx.snippets:
      base_path: ["."]          # so howto/commands.md can include the root POST_TRAINING.md
  - pymdownx.superfences:
      custom_fences:
        - name: mermaid
          class: mermaid
          format: !!python/name:pymdownx.superfences.fence_code_format
  - pymdownx.tabbed:
      alternate_style: true

extra_javascript:
  - https://unpkg.com/mermaid@11/dist/mermaid.min.js   # live hand-drawn mermaid in <details>
  - javascripts/mathjax.js
  - https://unpkg.com/mathjax@3/es5/tex-mml-chtml.js

nav:
  - Home: README.md
  - Foundations:
      - Overview: foundations/README.md
      - Tokenization & Data Shapes: foundations/tokenization.md
      - Decoder-Only Transformer: foundations/transformer.md
      - Attention, Masks & Heads: foundations/attention.md
      - Objectives, Losses & Perplexity: foundations/objectives.md
      - Optimization & Training Systems: foundations/optimization.md
      - Generation & Sampling: foundations/generation.md
  - Theory & Pipeline:
      - Data handling: 01_data_pipeline.md
      - Pretraining: 02_pretraining.md
      - SFT: 03_sft.md
      - Reward Model: 04_reward_model.md
      - DPO / ORPO / KTO: 05_dpo.md
      - PPO: 06_ppo.md
      - GRPO / RLVR: 07_grpo.md
  - How-to:
      - Configure (JSON): howto/configs.md
      - Train (UI & CLI): howto/train.md
      - The control-panel UI: howto/ui.md
      - Evaluate: 08_evaluation.md
      - Inference / Chat: 09_inference.md
  - Reference:
      - Command cheatsheet: howto/commands.md