{ "_name_or_path": "tiiuae/falcon-180B", "alibi": false, "architectures": [ "FalconForCausalLM" ], "attention_dropout": 0.0, "bias": false, "bos_token_id": 11, "eos_token_id": 11, "hidden_dropout": 0.0, "hidden_size": 14848, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "max_position_embeddings": 2048, "model_type": "falcon", "multi_query": true, "new_decoder_architecture": true, "num_attention_heads": 232, "num_hidden_layers": 140, "num_kv_heads": 8, "parallel_attn": true, "rope_scaling": null, "rope_theta": 10000.0, "torch_dtype": "float16", "transformers_version": "4.39.1", "use_cache": true, "vocab_size": 65024 }