Instructions to use codern/downstream-german-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codern/downstream-german-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="codern/downstream-german-bert")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("codern/downstream-german-bert") model = AutoModelForTokenClassification.from_pretrained("codern/downstream-german-bert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from codern/downstream-german-bert: direct link, hf CLI and curl.
- Browser
- Download file 438 MB
-
https://huggingface.co/codern/downstream-german-bert/resolve/refs%2Fpr%2F1/pytorch_model.bin
- Command line
-
hf download hf://codern/downstream-german-bert@refs/pr/1/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/codern/downstream-german-bert/resolve/refs%2Fpr%2F1/pytorch_model.bin
438 MB
- Xet hash:
- 1406b4fd6b6bbfd97853e175953bd16af490db4b0b7f80174b856a17d0fee16c
- Size of remote file:
- 438 MB
- SHA256:
- 89cb8e15af7d838a49e29bea011f538ca491d35617e195a5dd49e7473efdbef7
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.