# cgpotts/cs224u

Code for Stanford CS224u

Repository: https://github.com/cgpotts/cs224u
Canonical: https://ross.abutalabs.com/products/cs224u
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2025-02-28T06:49:53+00:00

## Health v2 (maintenance only)
Score: 36/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 9, release rhythm 35, longevity 100
- inputs: {"age_days": 4233, "days_push": 551, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2192, forks 911 (observed 2026-08-28T04:06:24.954143+00:00)

## What it is
The official code repository for Stanford's CS224u course on Natural Language Understanding, containing Jupyter notebook tutorials, homework assignments, and PyTorch model implementations. It covers topics like vector-space semantics, sentiment analysis, fine-tuning pretrained models, and model explainability.

## Use cases
- learn natural language understanding from scratch
- study PyTorch implementations of NLP models
- find course materials for teaching an NLP class
- understand GloVe and vector space models of meaning
- learn how to fine-tune Hugging Face transformers
- practice sentiment analysis on the Stanford Sentiment Treebank
- explore model explainability and feature attribution techniques

## When to choose
- you want a structured, university-level introduction to NLU
- you prefer learning through hands-on Jupyter notebooks with runnable code
- you need reference PyTorch implementations of classifiers, RNNs, and tree-structured networks
- you are an instructor looking for ready-made NLP course materials

## When to avoid
- you need a production-ready NLP library or framework
- you want maintained, versioned software with a stable API rather than teaching code
- you are looking for state-of-the-art LLM tooling beyond fine-tuning basics

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, nlp, deep-learning, developer-tools
- domain: machine-learning, education, tutorials
- platform: python, cross-platform
- tags: course-materials, stanford, pytorch, jupyter-notebooks, sentiment-analysis, vector-space-models, fine-tuning, explainability, natural-language-processing

## Member repositories
- cgpotts/cs224u (main) score 36

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:24.954143+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:47:26.052083+00:00, confidence not recorded.
  - readme: https://github.com/cgpotts/cs224u (fetched 2026-08-28T04:06:24.954143+00:00, sha 5a27c88bd048)
- Data as of 2026-08-30T08:39:29.467469+00:00.