Instructions to use neuralmind/bert-base-portuguese-cased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use neuralmind/bert-base-portuguese-cased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="neuralmind/bert-base-portuguese-cased")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("neuralmind/bert-base-portuguese-cased") model = AutoModelForMaskedLM.from_pretrained("neuralmind/bert-base-portuguese-cased", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
ValueError: Layer #0 (named "bert") expects 199 weight(s), but the saved weights have 197 element(s).
#4
by eduartheinen - opened
Hi. I'm getting this error when I try to load the LM in Transformers:ValueError: Layer #0 (named "bert") expects 199 weight(s), but the saved weights have 197 element(s).
Tried changing the model_name parameter but 'bert' is the same that appears in the model's config.yml file.