xmarva/transformer-architectures
Teaching transformer-based architectures
This collection of notebooks helps machine learning engineers and researchers understand how Transformer neural networks work by guiding them through building one from scratch. You'll work with raw text data, learn how to prepare it for models, implement the core components of Transformers like attention mechanisms, and then train these models. The output is a deep, practical understanding of advanced natural language processing architectures.
No commits in the last 6 months.
Use this if you are a machine learning practitioner looking to build a foundational understanding of Transformer architectures, from basic components to training complete models like BERT or GPT.
Not ideal if you are looking for a plug-and-play solution or an application-focused tool to solve a specific NLP problem without delving into the underlying model architecture.
Stars
7
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
May 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/xmarva/transformer-architectures"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
xv44586/toolkit4nlp
transformers implement (architecture, task example, serving and more)
luozhouyang/transformers-keras
Transformer-based models implemented in tensorflow 2.x(using keras).
ufal/neuralmonkey
An open-source tool for sequence learning in NLP built on TensorFlow.
graykode/xlnet-Pytorch
Simple XLNet implementation with Pytorch Wrapper
uzaymacar/attention-mechanisms
Implementations for a family of attention mechanisms, suitable for all kinds of natural language...