{ "architectures": [ "RoboBrainAudioForConditionalGeneration" ], "auto_map": { "AutoConfig": "configuration_robobrain_audio.RoboBrainAudioConfig", "AutoModelForCausalLM": "modeling_robobrain_audio.RoboBrainAudioForConditionalGeneration", "AutoProcessor": "processing_robobrain_audio.RoboBrainAudioProcessor" }, "audio_config": { "_attn_implementation": "eager", "activation_dropout": 0.0, "activation_function": "gelu", "attention_dropout": 0.1, "d_model": 1280, "deepstack_encoder_layer_indexes": [ 8, 16, 24 ], "downsample_hidden_size": 480, "downsample_rate": 8, "dropout": 0.1, "encoder_attention_heads": 20, "encoder_attention_window_size": 100, "encoder_ffn_dim": 5120, "encoder_layers": 32, "layer_norm_eps": 1e-05, "max_source_positions": 1500, "num_mel_bins": 128, "output_dim": 1280, "pretrained_path": "" }, "vision_config": { "deepstack_visual_indexes": [ 5, 11, 17 ], "depth": 24, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1024, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 4096, "model_type": "qwen3_vl", "num_heads": 16, "num_position_embeddings": 2304, "out_hidden_size": 2560, "patch_size": 16, "spatial_merge_size": 2, "temporal_patch_size": 2 }, "text_config": { "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 9728, "max_position_embeddings": 262144, "model_type": "qwen3_vl_text", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_interleaved": true, "mrope_section": [ 24, 20, 20 ], "rope_type": "default" }, "rope_theta": 5000000, "tie_word_embeddings": true, "use_cache": true, "vocab_size": 151936 }, "audio_token_id": 151654, "audio_start_token_id": 151669, "audio_end_token_id": 151670, "adapter_hidden_size": 8192, "audio_deepstack_inject_layers": 3, "ignore_index": -100, "bos_token_id": 151643, "eos_token_id": 151645, "image_token_id": 151655, "video_token_id": 151656, "vision_start_token_id": 151652, "vision_end_token_id": 151653, "model_type": "robobrain_audio", "num_hidden_layers": 36, "vocab_size": 151936, "tie_word_embeddings": true, "transformers_version": "4.57.0" }