{ "architectures": [ "Transformer" ], "d_model": 512, "dim_feedforward": 2048, "dropout": 0.1, "max_src_len": 1024, "max_tgt_len": 200, "model_type": "transformer", "nhead": 8, "num_decoder_layers": 6, "num_encoder_layers": 6, "torch_dtype": "float32", "transformers_version": "4.41.2", "vocab_size": 32104 }