Instructions to use CollectionStudio/ModernBERT-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CollectionStudio/ModernBERT-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="CollectionStudio/ModernBERT-large")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("CollectionStudio/ModernBERT-large") model = AutoModelForMaskedLM.from_pretrained("CollectionStudio/ModernBERT-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download onnx/model_uint8.onnx from CollectionStudio/ModernBERT-large: direct link, hf CLI and curl.
- Browser
- Download file 398 MB
-
https://huggingface.co/CollectionStudio/ModernBERT-large/resolve/main/onnx/model_uint8.onnx
- Command line
-
hf download hf://CollectionStudio/ModernBERT-large/onnx/model_uint8.onnx
-
curl -L -o model_uint8.onnx https://huggingface.co/CollectionStudio/ModernBERT-large/resolve/main/onnx/model_uint8.onnx
398 MB
- Xet hash:
- 3423309b0eac38ef4c4ed2b044fae8aaaa4f910229caba1efca55c1a146b37a6
- Size of remote file:
- 398 MB
- SHA256:
- 9020c46e799c51965677e0fd85fabb43eabfeb3d2e0bb686d11166bb6052c4f1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.