huseinzol05/albert-tiny-bahasa-cased

Pretrained Albert tiny language model for Malay and Indonesian, 85% faster execution and 50% smaller than Albert base . We trained on both standard and social media language structures . The model was trained using Google Albert's Github repository on v3-8 TPU . You can use this model by installing torch or tensorflow and Huggingface library transformers . And you can use it directly by initializing it like this: Initializing it using AlbertTokenizer, AlbertModelmodel = BertModel.from_pretrained('huseinzol05/albert-tiny-bahasa-cased') The output is, 'sequence': '[CLS],