huseinzol05/electra-small-generator-bahasa-cased

The Electra-small-generator-bahasa-cased model was pretrained on ~1.8 Billion words . We trained on both standard and social media language structures . The model was trained using Google ELECTRA's Github repository on a single TESLA V100 32GB VRAM . 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 AutoModelWithLMHead.from_pretrained('huseinzol05/electra/bahasa/cased') The output is, 'sequence': '[CLS],