loodos/bert-base-turkish-cased

Turkish Language Models with Huggingface's Transformers . We release cased and uncased versions of most recent language models for Turkish . More details about pretrained models and evaluations on downstream tasks can be found here (our repo) Turkish BERT-Base (cased) has 12 encoder layers with 768 hidden layer size trained on cased Turkish dataset .Using AutoModel and AutoTokenizer from Transformers, you can import the model as described below . You contact us to ask a question, open an issue or give feedback via our GitHub repo . Thank TFRC Team for providing us cloud TPUs on Tensorflow Research Cloud to train our models . For more information, please visit our repo,