jplu/tf-xlm-roberta-large

XLM-RoBERTa is a scaled cross lingual sentence encoder . XLM-R achieves state-of-the-arts results on multiple cross-lingual benchmarks . All models are available on the Huggingface model hub for Tensorflow . The model is trained on 2.5T of data across 100 languages data filtered from Common Crawl . The models can be loaded like: TFXLMRobertaModel.from_pretrained("jplu/tf-xlm-roberta-base") or TF_model.h5/TF-model.json • TF_Model.html • TF-Model.hs/tf_model,