config.json

{
  "architectures": [
    "PeAudioFrameLevelModel"
  ],
  "audio_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "dac_config": {
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "codebook_dim": 128,
      "codebook_loss_weight": 1.0,
      "codebook_size": 1024,
      "commitment_loss_weight": 0.25,
      "cross_attention_hidden_size": null,
      "decoder_hidden_size": 1536,
      "decoder_start_token_id": null,
      "downsampling_ratios": [
        2,
        8,
        10,
        12
      ],
      "dtype": null,
      "encoder_hidden_size": 64,
      "eos_token_id": null,
      "finetuning_task": null,
      "hidden_size": 1024,
      "hop_length": 1920,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "model_type": "dac",
      "n_codebooks": 16,
      "output_attentions": false,
      "output_hidden_states": false,
      "pad_token_id": null,
      "prefix": null,
      "problem_type": null,
      "quantizer_dropout": 0,
      "return_dict": true,
      "sampling_rate": 48000,
      "sep_token_id": null,
      "task_specific_params": null,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "upsampling_ratios": [
        12,
        10,
        8,
        2
      ]
    },
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 2048,
    "max_position_embeddings": 10000,
    "model_type": "pe_audio_encoder",
    "num_attention_heads": 6,
    "num_hidden_layers": 12,
    "num_key_value_heads": 6,
    "rms_norm_eps": 1e-05,
    "rope_parameters": {
      "rope_theta": 20000,
      "rope_type": "default"
    }
  },
  "dtype": "float32",
  "model_type": "pe_audio",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "classifier_activation": "gelu",
    "classifier_bias": false,
    "classifier_dropout": 0.0,
    "classifier_pooling": "cls",
    "cls_token_id": 50281,
    "decoder_bias": true,
    "deterministic_flash_attn": false,
    "embedding_dropout": 0.0,
    "global_attn_every_n_layers": 3,
    "hidden_activation": "gelu",
    "hidden_size": 1024,
    "initializer_cutoff_factor": 2.0,
    "initializer_range": 0.02,
    "intermediate_size": 2624,
    "layer_types": [
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention"
    ],
    "local_attention": 128,
    "max_position_embeddings": 8192,
    "mlp_bias": false,
    "mlp_dropout": 0.0,
    "model_type": "modernbert",
    "norm_bias": false,
    "norm_eps": 1e-05,
    "num_attention_heads": 16,
    "num_hidden_layers": 22,
    "repad_logits_with_grad": false,
    "rope_parameters": {
      "full_attention": {
        "rope_theta": 160000.0,
        "rope_type": "default"
      },
      "sliding_attention": {
        "rope_theta": 10000.0,
        "rope_type": "default"
      }
    },
    "sparse_pred_ignore_index": -100,
    "sparse_prediction": false,
    "vocab_size": 50368
  },
  "transformers_version": "5.0.0.dev0"
}