{ "architectures": [ "LlamaModel" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128012, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 11008, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "loss_type": "CausalLMLoss", "max_position_embeddings": 65536, "max_window_layers": 28, "mlp_bias": false, "model_type": "llama", "no_rope_layer_interval": 4, "no_rope_layers": [ 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0 ], "num_attention_heads": 16, "num_hidden_layers": 36, "num_key_value_heads": 4, "pad_token_id": 128004, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.53.2", "use_cache": false, "use_sliding_window": false, "vocab_size": 128256 }