{ "architectures": [ "EnsembleForCausalLM" ], "auto_map": { "AutoConfig": "ensemble_qwen.EnsembleConfig", "AutoModelForCausalLM": "ensemble_qwen.EnsembleForCausalLM" }, "model_a_path": "Qwen/Qwen3-4B", "model_b_path": "Qwen/Qwen3-4B-Base", "model_type": "ensemble_qwen", "torch_dtype": "bfloat16", "transformers_version": "4.51.3", "weight_a": 0.5, "weight_b": 0.5, "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 9728, "max_position_embeddings": 40960, "max_window_layers": 36, "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "sliding_window": null, "tie_word_embeddings": true, "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }