{ "model_name": "Alpha-Transformer", "model_type": "encoder-decoder-transformer", "d_model": 256, "num_heads": 8, "d_ff": 1024, "num_encoder_layers": 3, "num_decoder_layers": 3, "src_vocab_size": 51278, "tgt_vocab_size": 63558, "max_seq_length": 64, "rope_max_seq_length": 1024, "positional_encoding": "RoPE", "activation": "ReLU", "normalization": "Pre-LayerNorm", "num_parameters": 51262022, "dataset": "OPUS-100", "task": "English-French machine translation", "framework": "PyTorch", "pad_token_id": 0, "unk_token_id": 1, "bos_token_id": 2, "eos_token_id": 3 }