{
  "transformers_version": "5.5.0",
  "architectures": [
    "Gemma4AudioModel"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "dtype": "bfloat16",
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "problem_type": null,
  "hidden_size": 1024,
  "num_hidden_layers": 12,
  "num_attention_heads": 8,
  "hidden_act": "silu",
  "subsampling_conv_channels": [
    128,
    32
  ],
  "conv_kernel_size": 5,
  "residual_weight": 0.5,
  "attention_chunk_size": 12,
  "attention_context_left": 13,
  "attention_context_right": 0,
  "attention_logit_cap": 50.0,
  "attention_invalid_logits_value": -1000000000.0,
  "use_clipped_linears": true,
  "rms_norm_eps": 1e-06,
  "gradient_clipping": 10000000000.0,
  "output_proj_dims": 1536,
  "initializer_range": 0.02,
  "_name_or_path": "",
  "model_type": "gemma4_audio",
  "output_attentions": false,
  "torch_dtype": "bfloat16",
  "_verified_total_params": 304824608,
  "_verified_hidden_dim": 1024,
  "_verified_output_dim": 1536,
  "_verified_num_layers": 12,
  "_verified_num_heads": 8,
  "_verified_head_dim": 128,
  "_verified_ffn_intermediate": 4096,
  "_verified_conv_kernel": 5,
  "_verified_subsampling_channels": [
    128,
    32
  ],
  "_verified_subsampling_norm": "LayerNorm",
  "_verified_subsampling_activation": "ReLU",
  "_verified_conformer_activation": "SiLU",
  "_verified_conformer_norm": "RMSNorm",
  "_verified_conformer_norm_eps": 1e-06,
  "_verified_temporal_downsample": 4,
  "_source_model": "google/gemma-4-E2B-it",
  "_extraction_note": "Audio tower weights are identical between E2B and E4B variants"
}