Instructions to use ltg/norbert3-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ltg/norbert3-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="ltg/norbert3-base", trust_remote_code=True)# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("ltg/norbert3-base", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Not compatible with AutoTrain
Trying to use the model with the HF autotrainer but the training is being stopped. ltg/norbert2 works but not the new version.
Hi, our new models use a custom architecture, which is probably why it's not working. Can you give us more information about this error? Maybe there's a way to fix it :)
Hi, is it possible to use Norbert3-base to do text categorisation? if yes, could you give me an example how to use it? thanks.
Hi, you will probably have to import NorBERT as AutoModelForSequenceClassification and finetune it on your dataset.
Sorry for not responding but AutoTrain doesn't exactly yield an informative error. I haven't tested it in months so it may have changed. However, last time it looked like it could load the model properly.