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
Accelerating over 130,000 Hugging Face models with ONNX Runtime
Hugging Face Blog · 2 years ago ·
15
The Transformer Family Version 2.0
Lilian Weng · 3 years ago ·
42
Pre-Train BERT with Hugging Face Transformers and Habana Gaudi
Hugging Face Blog · 3 years ago ·
49
Hugging Face's TensorFlow Philosophy
Hugging Face Blog · 3 years ago ·
21
Graphcore and Hugging Face Launch New Lineup of IPU-Ready Transformers
Hugging Face Blog · 4 years ago ·
1
Getting Started with Transformers on Habana Gaudi
Hugging Face Blog · 4 years ago ·
40
Accelerate BERT inference with Hugging Face Transformers and AWS Inferentia
Hugging Face Blog · 4 years ago ·
30
BERT 101 - State Of The Art NLP Model Explained
Hugging Face Blog · 4 years ago ·
44
2023
2022
- Pre-Train BERT with Hugging Face Transformers and Habana Gaudi
- Hugging Face's TensorFlow Philosophy
- Graphcore and Hugging Face Launch New Lineup of IPU-Ready Transformers
- Getting Started with Transformers on Habana Gaudi
- Accelerate BERT inference with Hugging Face Transformers and AWS Inferentia
- BERT 101 - State Of The Art NLP Model Explained
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
- Large Language Models: A New Moore's Law?
- How to Win a Data Hackathon (Hacklytics 2021)
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