Hugging Face Uses Block Pruning to Speedup Transformer Training While Maintaining Accuracy

Retrieved on: 2021-09-21 13:41:15

Tags for this article:

Artificial intelligence

Academic disciplines

Learning

Machine learning

Artificial neural networks

Deep learning

Speech recognition

Transformer

Decision tree pruning

Language model

Natural language processing

Pruning

Click the tags to see associated articles and topics

Hugging Face Uses Block Pruning to Speedup Transformer Training While Maintaining Accuracy. View article details on hiswai:

Excerpt

For instance, training Open AI's GPT-3, which has 175 billion parameters, ... the Hugging Face researchers focus on three recent varieties of large-scale ...

Article found on: syncedreview.com

View Original Article