{ "_name_or_path": "./xglm-564M_models/en/2016_bytes", "activation_dropout": 0, "activation_function": "gelu", "architectures": [ "XGLMModel" ], "attention_dropout": 0.1, "attention_heads": 16, "bos_token_id": 0, "d_model": 1024, "decoder_start_token_id": 2, "dropout": 0.1, "eos_token_id": 2, "ffn_dim": 4096, "init_std": 0.02, "layerdrop": 0.0, "max_position_embeddings": 2048, "model_type": "xglm", "num_layers": 24, "pad_token_id": 1, "scale_embedding": true, "torch_dtype": "float32", "transformers_version": "4.18.0", "use_cache": true, "vocab_size": 256008 }