Código del video:
https://github.com/JACantoral/DL_fundamentals/blob/main/DL_fundamentals_transformer_model.ipynb
Videos previos acerca de Transformers
Parte 1 - https://youtu.be/Bh22yyEJFak
Parte 2 - https://youtu.be/Nj5DVykeFhM
Parte 3 - https://youtu.be/AFcqsswq3C8
Embeddings
Desde cero - https://youtu.be/8f9H-7i2RAw
Teoria - https://youtu.be/LagcbjDkqJE
Cómo codificar un Transformer original de "Attention is All You Need" desde cero usando PyTorch
En este tutorial, explico cómo implementar desde cero el famoso modelo de Transformer presentado en el artículo "Attention is All You Need". Utilizando PyTorch, cubriremos todos los aspectos fundamentales del Transformer, incluyendo encoder, decoder, las capas de multi head attention, y posicional encoding.
Continue this lesson in the app
Install CourseHive on Android or iOS to keep learning while you move.
FAQs
We curate free YouTube courses, organized by category and language — and make it easy for you to track your learning progress.
Yes. Free courses are embedded YouTube videos.
Currently available in English — with Portuguese, Spanish, French, German, and Italian coming soon.
Check ratings, reviews, duration, and description.
All courses include a certificate of participation.
Yes, an account lets you track progress, earn certificates, and save favorites.
We auto-save your watch position so you can resume on any device.