SkalskiP/vlms-zero-to-hero
A tutorial series teaching Vision-Language Models from NLP and Computer Vision fundamentals through Jupyter notebook implementations.
Velocity · 7d
+2.2
★ / day
Trend
→steady
star history
This repository is a structured learning resource covering the fundamentals of NLP and Computer Vision, progressing toward Vision-Language Models. It includes Jupyter notebooks implementing key concepts like Word2Vec, BERT, GPT, and CLIP with PyTorch, referencing foundational papers and providing Colab links for interactive learning.