Instructions to use google-bert/bert-base-uncased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google-bert/bert-base-uncased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="google-bert/bert-base-uncased")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-uncased") model = AutoModelForMaskedLM.from_pretrained("google-bert/bert-base-uncased") - Inference
- Notebooks
- Google Colab
- Kaggle
BERT β the grandfather of modern mobile NLP
#107
by 3morixd - opened
60 million downloads. BERT may be old (2018), but it's still running on millions of phones worldwide.
For simple classification tasks (sentiment, spam detection, intent classification), BERT is still the best choice:
- 420MB (full) or 110MB (Tiny)
- <10ms inference on phone
- Battle-tested, no surprises
- TensorFlow Lite compatible
At Dispatch AI, we use BERT alongside modern small LLMs β BERT for classification, LLM for generation. The right tool for the right job.
Respect to Google for this foundational model. π
β Dispatch AI (FZE), Sharjah UAE