BERT
BERT is a 2018 machine learning model developed by Google that uses bidirectional learning to handle natural language processing tasks such as sentiment analysis and named entity recognition. Recent coverage shows BERT being optimized and deployed across various hardware platforms including ONNX Runtime, AWS Inferentia, Habana Gaudi accelerators, and Graphcore IPUs through Hugging Face libraries, with implementations achieving significant improvements in inference latency and cost efficiency.
Updated 3 August 2026
Specifications
No specifications recorded yet.
Latest developments
October 2023
January 2023
August 2022
May 2022
April 2022
March 2022
- Accelerate BERT inference with Hugging Face Transformers and AWS Inferentia
- BERT 101 - State Of The Art NLP Model Explained
November 2021
- Getting Started with Hugging Face Transformers for IPUs with Optimum
- Fine-Tune XLSR-Wav2Vec2 for low-resource ASR with 🤗 Transformers
- Scaling up BERT-like model Inference on modern CPU - Part 2
October 2021
February 2021
January 2019
Relationships
Products & technology
- Hugging Face integrated with this model · 2 sources
- Google develops this model · 1 source
- Google integrated with this model · 1 source
- Graphcore integrated with this model · 1 source
- Intel integrated with this model · 1 source
- DistilBERT derived from this model · 1 source
- Hugging Face deploys this model · 1 source