{ "vocab_size": 32000, "min_frequency": 2, "show_progress": true, "special_tokens": [ "[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]" ], "lowercase": false, "dropout": null, "data_dir": "./data", "model_save_dir": "models", "model_name": "EthioBBPE", "use_checkpoint": true, "checkpoint_dir": "./models/checkpoints", "save_compressed": true, "checkpoint_steps": null, "num_threads": -1 }