runtimelab▮
Sign in

~/runtimelab $ cat ./embeddings/README

Build your own Embeddings

Build word and sentence embeddings from scratch — co-occurrence counts, PPMI, truncated SVD, then skip-gram with negative sampling — and measure them against analogy and similarity benchmarks instead of eyeballing a nearest-neighbour list.

what you end up with
An embedding model, trained and benchmarked

stages
0
level
Intermediate
track
AI/ML Engineering
language
Python
  • the co-occurrence matrix
  • PPMI, and why raw counts fail
  • truncated SVD and the dimension you keep
  • skip-gram with negative sampling
  • subsampling and the noise distribution
  • analogy and similarity benchmarks
  • contrastive sentence embeddings
  • why mean-pooling a token model is the wrong answer
Sign in to startBrowse all challenges

The stage list opens once you sign in — it is the challenge, not the pitch. Signing in is free, and the first stages of every challenge are too.