Quantization is one of the most common techniques to make language models smaller and more practical. The idea is simple – instead of storing model weights with high numerical precision, these are replaced with lower precision approximations. This reduces the …
This is a small, but surprisingly whole and satisfying project – we take a wine review of a few sentences and we train a tiny neural network to guess which grape it is from. No images, no GPU, no advanced …
Predict Wine Variety from text: Embeddings + PyTorch Read more →
In the article from 1984, Fredman and Komlos (1) mention the perfect hash function, that actually can store a sparse table with 0(1) worst case access time. And as they mention that both the data structure and the query algorithm …
Searching through 399 documents or 40 web pages (the numbers are not random) can be a tough task if you rely on standard tools like ctrl+f. When the data grows, you need a dedicated search engine that understands relevance, handles …
BFS, DFS, A-Star – these sound like magic spells from a Harry Potter book! And actually, these are magical (especially the A-Star) as far as they are well-defined algorithms, that explore a graph. In our previous article, we have explored …
Breadth-First Search (BFS) algorithm with Python Read more →