{
  "architectures": [
    "PeAudioVideoEncoder"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "audio_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "dac_config": {
      "_name_or_path": "",
      "architectures": null,
      "chunk_size_feed_forward": 0,
      "codebook_dim": 32,
      "codebook_loss_weight": 1.0,
      "codebook_size": 512,
      "commitment_loss_weight": 0.25,
      "decoder_hidden_size": 16,
      "downsampling_ratios": [
        2,
        4,
        4
      ],
      "dtype": null,
      "encoder_hidden_size": 16,
      "hidden_size": 128,
      "hop_length": 32,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "model_type": "dac",
      "n_codebooks": 6,
      "output_attentions": false,
      "output_hidden_states": false,
      "problem_type": null,
      "quantizer_dropout": 0.0,
      "return_dict": true,
      "sampling_rate": 16000,
      "upsampling_ratios": [
        4,
        4,
        2
      ]
    },
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 32,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "max_position_embeddings": 512,
    "max_window_layers": 28,
    "model_type": "pe_audio_encoder",
    "num_attention_heads": 2,
    "num_hidden_layers": 2,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-05,
    "rope_parameters": {
      "rope_theta": 20000,
      "rope_type": "default"
    }
  },
  "dtype": "float32",
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 32,
  "initializer_range": 0.02,
  "intermediate_size": 37,
  "max_position_embeddings": 512,
  "max_window_layers": 28,
  "model_type": "pe_audio_video_encoder",
  "num_attention_heads": 2,
  "num_hidden_layers": 2,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 20000,
    "rope_type": "default"
  },
  "transformers_version": "5.16.0.dev0",
  "video_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 32,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "max_position_embeddings": 512,
    "max_window_layers": 28,
    "model_type": "pe_video_encoder",
    "num_attention_heads": 2,
    "num_hidden_layers": 2,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-05,
    "rope_parameters": {
      "rope_theta": 20000,
      "rope_type": "default"
    },
    "vision_config": {
      "_name_or_path": "",
      "architecture": "vit_pe_core_large_patch14_336",
      "architectures": null,
      "chunk_size_feed_forward": 0,
      "do_pooling": true,
      "dtype": null,
      "global_pool": "map",
      "initializer_range": 0.02,
      "is_encoder_decoder": false,
      "label_names": [
        "LABEL_0",
        "LABEL_1",
        "LABEL_2",
        "LABEL_3"
      ],
      "model_args": {
        "depth": 2,
        "embed_dim": 64,
        "img_size": [
          14,
          14
        ]
      },
      "model_type": "timm_wrapper",
      "num_classes": 4,
      "output_attentions": false,
      "output_hidden_states": false,
      "problem_type": null,
      "return_dict": true
    }
  }
}