Roberta TR Medium Wp 44k

🚀 RoBERTa Turkish medium WordPiece 44k (uncased)

This is a pre - trained model on the Turkish language, which uses a masked language modeling (MLM) objective. It aims to provide effective language - related capabilities for Turkish text processing.

🚀 Quick Start

This is a pre - trained model on the Turkish language using a masked language modeling (MLM) objective. The model is uncased. The pretrained corpus is OSCAR's Turkish split, which has been further filtered and cleaned.

The model architecture is similar to bert - medium (8 layers, 8 heads, and 512 hidden size). The tokenization algorithm is WordPiece, and the vocabulary size is 44.5k.

The details can be found in this paper: https://arxiv.org/abs/2204.08832

💻 Usage Examples

Basic Usage

# The following code can be used for model loading and tokenization, example max length (514) can be changed:
model = AutoModel.from_pretrained([model_path])
#for sequence classification:
#model = AutoModelForSequenceClassification.from_pretrained([model_path], num_labels=[num_classes])

tokenizer = PreTrainedTokenizerFast(tokenizer_file=[file_path])
tokenizer.mask_token = "[MASK]"
tokenizer.cls_token = "[CLS]"
tokenizer.sep_token = "[SEP]"
tokenizer.pad_token = "[PAD]"
tokenizer.unk_token = "[UNK]"
tokenizer.bos_token = "[CLS]"
tokenizer.eos_token = "[SEP]"
tokenizer.model_max_length = 514

📄 License

The model is licensed under cc - by - nc - sa - 4.0.

BibTeX entry and citation info

@misc{https://doi.org/10.48550/arxiv.2204.08832,
  doi = {10.48550/ARXIV.2204.08832},
  url = {https://arxiv.org/abs/2204.08832},
  author = {Toraman, Cagri and Yilmaz, Eyup Halit and Şahinuç, Furkan and Ozcelik, Oguzhan},
  keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Impact of Tokenization on Language Models: An Analysis for Turkish},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}

📚 Documentation