huseinzol05/electra-base-generator-bahasa-cased

The Electra-base-generator-bahasa-cased model was pretrained on ~1.8 Billion words . We trained on both standard and social media language structures, and below is list of data we trained on . The model was trained using Google ELECTRA's Github repository on v3-8 TPU . All steps can reproduce from here, Malaya/pretrained-model/electra.html, and you can use it directly by installing torch or tensorflow and Huggingface library transformers . The output is, 'sequence': '[CLS] makan ayam dengan [MASK]], 'score': 0.084248,