{ "architectures": [ "StepAudio2ForCausalLM" ], "audio_encoder_config": { "llm_dim": 3584, "model_type": "step_audio_2_encoder", "n_audio_head": 20, "n_audio_layer": 32, "n_audio_state": 1280, "n_codebook_size": 4096 }, "auto_map": { "AutoConfig": "configuration_step_audio_2.StepAudio2Config", "AutoModelForCausalLM": "modeling_step_audio_2.StepAudio2ForCausalLM" }, "max_window_layers": null, "model_type": "step_audio_2", "sliding_window": 2048, "text_config": { "_attn_implementation_autoset": true, "architectures": [ "Qwen2ForCausalLM" ], "hidden_size": 3584, "intermediate_size": 18944, "max_position_embeddings": 16384, "model_type": "qwen2", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rope_theta": 1000000.0, "torch_dtype": "bfloat16", "vocab_size": 238352 }, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_sliding_window": false }