# nguynking/cs224n architecture

> Architecture diagram of the GitHub repository nguynking/cs224n, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-09-13). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/nguynking/cs224n
- Repository: https://github.com/nguynking/cs224n

## Overview

##### Project type and purpose
- This repository is primarily a student’s collection of solutions for the Stanford CS224N assignments (A1–A5), plus a “minBERT” final project under project/minbert-default-final-project-main.
- The “minBERT” subfolder is a standalone NLP tool: a small‐scale BERT-style model supporting tokenization, pretraining, fine-tuning, and multitask classification on several datasets.

##### File structure
- Top-level:
├ .gitignore
├ README.md (course overview)
├ requirements.txt
├ assignment1 … assignment5 (each a self-contained homework)
└ project/minbert-default-final-project-main (the final project)
- In the minBERT project folder:
– Configuration & setup: config.py, setup.sh, run.sh, prepare_submit.py
– Data & preprocessing: data/*.csv, tokenizer.py, datasets.py
– Model definitions: base_bert.py, bert.py, classifier.py, multitask_classifier.py
– Training loop: optimizer.py, evaluation.py, sanity_check.py
– Utilities: utils.py
– Predictions output directory

##### README for additional insights
- The high-level README emphasizes CS224N course solutions; the “Future works” note calls out completion of minBERT.
- The project subfolder has its own README.md and STRUCTURE.md (not shown), which likely describe the training/evaluation phases.

##### Detailed elements to capture
– datasets.py and tokenizer.py grouped as “Data Prep”
– base_bert.py, bert.py, classifier.py, multitask_classifier.py grouped as “Model Library”
– optimizer.py + run script as “Training Pipeline”
– evaluation.py + predictions folder as “Evaluation/Submission”
– config.py centrally feeding into all components

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Data Preparation Layer
    subgraph "Data Preparation"
        D1["Data Files (CSV)"]:::data
        D2["datasets.py"]:::data
        D3["tokenizer.py"]:::data
    end

    %% Model Library Layer
    subgraph "Model Library"
        M1["base_bert.py"]:::model
        M2["bert.py"]:::model
        M3["classifier.py"]:::model
        M4["multitask_classifier.py"]:::model
    end

    %% Training Pipeline Layer
    subgraph "Training Pipeline"
        T1["optimizer.py"]:::training
        S1["run.sh"]:::training
        S2["prepare_submit.py"]:::training
        SC1["sanity_check.py"]:::training
        SC2["sanity_check.data"]:::training
    end

    %% Evaluation / Submission Layer
    subgraph "Evaluation/Submission"
        E1["evaluation.py"]:::eval
        E2["predictions (CSV)"]:::eval
    end

    %% Configuration & Utilities
    Config["config.py"]:::config
    Utils["utils.py"]:::config

    %% Data Flow
    D1 --> D2
    D2 --> D3
    D3 --> M1
    M1 --> M2
    M2 --> M3
    M2 --> M4
    M3 --> T1
    M4 --> T1
    T1 --> S1
    S1 --> SC1
    S1 --> E1
    S2 --> T1
    SC1 --> S2
    E1 --> E2

    %% Configuration & Utilities Connections
    Config -.-> D2
    Config -.-> M1
    Config -.-> T1
    Config -.-> E1
    Utils -.-> D2
    Utils -.-> M1
    Utils -.-> T1
    Utils -.-> E1

    %% Click Events
    click D1 "https://github.com/nguynking/cs224n/tree/main/project/minbert-default-final-project-main/data"
    click D2 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/datasets.py"
    click D3 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/tokenizer.py"
    click M1 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/base_bert.py"
    click M2 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/bert.py"
    click M3 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/classifier.py"
    click M4 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/multitask_classifier.py"
    click T1 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/optimizer.py"
    click S1 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/run.sh"
    click S2 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/prepare_submit.py"
    click SC1 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/sanity_check.py"
    click SC2 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/sanity_check.data"
    click E1 "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/evaluation.py"
    click E2 "https://github.com/nguynking/cs224n/tree/main/project/minbert-default-final-project-main/predictions"
    click Config "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/config.py"
    click Utils "https://github.com/nguynking/cs224n/blob/main/project/minbert-default-final-project-main/utils.py"

    %% Styles
    classDef data fill:#ADD8E6,stroke:#000;
    classDef model fill:#90EE90,stroke:#000;
    classDef training fill:#FFA500,stroke:#000;
    classDef eval fill:#DDA0DD,stroke:#000;
    classDef config fill:#D3D3D3,stroke:#000;
```
