{
  "model_type": "qheart",
  "architectures": ["QHEARTForECGQA"],
  "auto_map": {
      "AutoConfig": "configuration_qheart.QHEARTConfig",
      "AutoModel": "modeling_qheart.QHEARTForECGQA",
      "AutoModelForCausalLM": "modeling_qheart.QHEARTForECGQA"
  },
  "encoder_layers": 12,
  "encoder_embed_dim": 768,
  "encoder_ffn_embed_dim": 3072,
  "encoder_attention_heads": 12,
  "layer_norm_first": false,
  "dropout": 0.1,
  "attention_dropout": 0.1,
  "activation_dropout": 0.0,
  "encoder_layerdrop": 0.0,
  "dropout_input": 0.1,
  "dropout_features": 0.1,
  "apply_mask": false,
  "mask_length": 10,
  "mask_prob": 0.0,
  "mask_selection": "static",
  "mask_other": 0.0,
  "no_mask_overlap": false,
  "mask_min_space": 1,
  "mask_channel_length": 10,
  "mask_channel_prob": 0.0,
  "mask_channel_selection": "static",
  "mask_channel_other": 0.0,
  "no_mask_channel_overlap": false,
  "mask_channel_min_space": 1,
  "extractor_mode": "default",
  "conv_feature_layers": "[(256, 2, 2)] * 4",
  "in_d": 12,
  "conv_bias": false,
  "feature_grad_mult": 1.0,
  "conv_pos": 128,
  "conv_pos_groups": 16,
  "load_pretrained_weights": false,
  "pretrained_model_path": "",
  "vocab_size": 32128,
  "hidden_dim": 768,
  "num_layers": 6,
  "num_heads": 12,
  "drop_rate": 0.1,
  "num_top_layer": 6,
  "mim_layer": 3,
  "mim_prob": 0.75,
  "mim_decoder_hidden_dim": 384,
  "mim_decoder_num_layers": 4,
  "mim_decoder_num_heads": 6,
  "max_text_size": 256,
  "llm_model_type": "meta-llama/Llama-3.2-1B-Instruct",
  "mapping_type": "Transformer",
  "prefix_length": 12,
  "clip_length": 12
}