Instructions to use distilbert/distilbert-base-cased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use distilbert/distilbert-base-cased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="distilbert/distilbert-base-cased")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("distilbert/distilbert-base-cased") model = AutoModelForMaskedLM.from_pretrained("distilbert/distilbert-base-cased", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download tf_model.h5 from distilbert/distilbert-base-cased: direct link, hf CLI and curl.
- Browser
- Download file 354 MB
-
https://huggingface.co/distilbert/distilbert-base-cased/resolve/refs%2Fpr%2F7/tf_model.h5
- Command line
-
hf download hf://distilbert/distilbert-base-cased@refs/pr/7/tf_model.h5
-
curl -L -o tf_model.h5 https://huggingface.co/distilbert/distilbert-base-cased/resolve/refs%2Fpr%2F7/tf_model.h5
354 MB
- Xet hash:
- df3d334396767d35298f5dd1877d53e83e050d21a65668c5aef179ac731d0b33
- Size of remote file:
- 354 MB
- SHA256:
- cead32d02b605245c06a87c760d32366261a445bd16ef0280c7543732a767099
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.