Ask HN: Can someone ELI5 Transformers and the “Attention is all we need” paper

• bertviz

  15 6,398 3.9 Python

  BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

The Illustrated Transfomer ( https://jalammar.github.io/illustrated-transformer/ ) and Visualizing attention ( https://towardsdatascience.com/deconstructing-bert-part-2-vi... ), are both really good resources. For a more ELI5 approach this non-technical explainer ( https://www.parand.com/a-non-technical-explanation-of-chatgp... ) covers it at a high level.

• things-to-talk-about

  1 2 6.1 TeX

  A collection of talks / presentations I created or held at some point.

Uhm nope but here's a ~70min talk I held about it: https://github.com/fkarg/things-to-talk-about/blob/master/tr...

Not sure how well the slides can be understood by themselves, though I tried to be accommodating for that

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project