Explore >> Select a destination

You are here

 harvardnlp.github.io
The Annotated Transformer
| | nlp.seas.harvard.edu
The Annotated Transformer
0.0 parsecs away

Travel
| | The Annotated Transformer
| | sigmoidprime.com
Transformer-XL: A Memory-Augmented Transformer
3.2 parsecs away

Travel
| | An exploration of Transformer-XL, a modified Transformer optimized for longer context length.
| | blog.eleuther.ai
Rotary Embeddings: A Relative Revolution | EleutherAI Blog
3.1 parsecs away

Travel
| | Rotary Positional Embedding (RoPE) is a new type of position encoding that unifies absolute and relative approaches. We put it to the test.
| | igorstechnoclub.com
Week 5 in Data Science: Image recognition neural network with 90% accuracy - a trivial task | Igor's Techno Club
12.9 parsecs away

Travel
| This week I learned something that finally made "transfer learning" click. I had always heard that you can hit strong accuracy fast by reusing a pretrain...