Instructions to use amazon/bort with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amazon/bort with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="amazon/bort")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("amazon/bort") model = AutoModelForMaskedLM.from_pretrained("amazon/bort", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signature4659f60
-
upload flax model
8f39f62 -
allow flax
444ceff
-
Update README.md
ce41997
-
config: fix tokenizer class
f39ac83 -
config: change model_type and tokenizer_class
It uses BERT for model and RoBERTa for tokenizer now1cd7ac7
-
README: add disclaimer
71e6a15
-
bort: add TensorFlow model
9090451 -
bort: add PyTorch model
ba07570 -
bort: add tokenizer-related files
0124d44 -
bort: add configuration
e6fb7d7 -
initial commit
a296fe4