{ "architectures": [ "AeroForConditionalGeneration" ], "audio_config": { "_attn_implementation_autoset": true, "activation_dropout": 0.0, "activation_function": "gelu", "attention_dropout": 0.0, "d_model": 1280, "dropout": 0.0, "encoder_attention_heads": 20, "encoder_ffn_dim": 5120, "encoder_layerdrop": 0.0, "encoder_layers": 32, "init_std": 0.02, "initializer_range": 0.02, "max_source_positions": 1500, "model_type": "qwen2_audio_encoder", "num_hidden_layers": 32, "num_mel_bins": 128, "scale_embedding": false, "torch_dtype": "bfloat16" }, "audio_token_index": 151667, "auto_map": { "AutoConfig": "configuration_aero.AeroConfig", "AutoModelForCausalLM": "modeling_aero.AeroForConditionalGeneration" }, "model_type": "aero", "text_config": { "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8960, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152000 }, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.52.0.dev0" }