BERTimbau Large Portuguese
| Property | Value |
|---|---|
| Parameter Count | 335M |
| Architecture | BERT-Large (24 layers) |
| License | MIT |
| Downloads | 295,940 |
What is bert-large-portuguese-cased?
BERTimbau Large is a state-of-the-art BERT model specifically trained for Brazilian Portuguese language processing. Developed by neuralmind, it represents one of the most comprehensive Portuguese language models available, featuring 24 layers and 335 million parameters.
Implementation Details
The model is built on the BERT-Large architecture and has been pretrained on the brWaC dataset. It maintains case sensitivity and can be easily implemented using the Hugging Face Transformers library. The model supports both masked language modeling and embedding generation tasks.
- 24-layer BERT architecture
- Case-sensitive tokenization
- Compatible with PyTorch and JAX
- Supports fill-mask operations
Core Capabilities
- Named Entity Recognition (NER)
- Sentence Textual Similarity
- Recognizing Textual Entailment
- Masked Language Modeling
- Contextual Embeddings Generation
Frequently Asked Questions
Q: What makes this model unique?
This model stands out for being one of the largest Portuguese language models available, specifically optimized for Brazilian Portuguese. Its large architecture (335M parameters) enables superior performance on various downstream NLP tasks.
Q: What are the recommended use cases?
The model excels in tasks such as named entity recognition, textual similarity analysis, and entailment recognition. It's particularly useful for applications requiring deep understanding of Brazilian Portuguese text, including text classification, information extraction, and semantic analysis.
