config.json

{
  "architectures": [
    "UltravoxModel"
  ],
  "audio_config": {
    "_name_or_path": "openai/whisper-small",
    "activation_dropout": 0.0,
    "activation_function": "gelu",
    "apply_spec_augment": false,
    "architectures": [
      "WhisperForConditionalGeneration"
    ],
    "attention_dropout": 0.0,
    "begin_suppress_tokens": [
      220,
      50257
    ],
    "bos_token_id": 50257,
    "d_model": 768,
    "decoder_attention_heads": 12,
    "decoder_ffn_dim": 3072,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 12,
    "decoder_start_token_id": 50258,
    "dropout": 0.0,
    "encoder_attention_heads": 12,
    "encoder_ffn_dim": 3072,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 12,
    "eos_token_id": 50257,
    "forced_decoder_ids": [
      [
        1,
        50259
      ],
      [
        2,
        50359
      ],
      [
        3,
        50363
      ]
    ],
    "init_std": 0.02,
    "is_encoder_decoder": true,
    "max_length": 448,
    "max_source_positions": 1500,
    "max_target_positions": 448,
    "median_filter_width": 7,
    "model_type": "whisper",
    "num_hidden_layers": 12,
    "num_mel_bins": 80,
    "pad_token_id": 50257,
    "scale_embedding": false,
    "suppress_tokens": [
      1,
      2,
      7,
      8,
      9,
      10,
      14,
      25,
      26,
      27,
      28,
      29,
      31,
      58,
      59,
      60,
      61,
      62,
      63,
      90,
      91,
      92,
      93,
      359,
      503,
      522,
      542,
      873,
      893,
      902,
      918,
      922,
      931,
      1350,
      1853,
      1982,
      2460,
      2627,
      3246,
      3253,
      3268,
      3536,
      3846,
      3961,
      4183,
      4667,
      6585,
      6647,
      7273,
      9061,
      9383,
      10428,
      10929,
      11938,
      12033,
      12331,
      12562,
      13793,
      14157,
      14635,
      15265,
      15618,
      16553,
      16604,
      18362,
      18956,
      20075,
      21675,
      22520,
      26130,
      26161,
      26435,
      28279,
      29464,
      31650,
      32302,
      32470,
      36865,
      42863,
      47425,
      49870,
      50254,
      50258,
      50360,
      50361,
      50362
    ],
    "torch_dtype": "float32",
    "use_cache": true,
    "vocab_size": 51865
  },
  "audio_model_id": "openai/whisper-small",
  "audio_token_index": 32000,
  "hidden_size": 4096,
  "ignore_index": -100,
  "initializer_range": 0.02,
  "model_type": "ultravox",
  "norm_init": 0.4,
  "projector_act": "swiglu",
  "stack_factor": 8,
  "text_config": {
    "_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
    "architectures": [
      "Phi3ForCausalLM"
    ],
    "attention_bias": false,
    "auto_map": {
      "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
      "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM",
      "AutoModelForSequenceClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForSequenceClassification",
      "AutoModelForTokenClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForTokenClassification"
    },
    "embd_pdrop": 0.0,
    "eos_token_id": 32000,
    "hidden_size": 3072,
    "intermediate_size": 8192,
    "max_position_embeddings": 131072,
    "model_type": "phi3",
    "original_max_position_embeddings": 4096,
    "pad_token_id": 32000,
    "resid_pdrop": 0.0,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "long_factor": [
        1.0299999713897705,
        1.0499999523162842,
        1.0499999523162842,
        1.0799999237060547,
        1.2299998998641968,
        1.2299998998641968,
        1.2999999523162842,
        1.4499999284744263,
        1.5999999046325684,
        1.6499998569488525,
        1.8999998569488525,
        2.859999895095825,
        3.68999981880188,
        5.419999599456787,
        5.489999771118164,
        5.489999771118164,
        9.09000015258789,
        11.579999923706055,
        15.65999984741211,
        15.769999504089355,
        15.789999961853027,
        18.360000610351562,
        21.989999771118164,
        23.079999923706055,
        30.009998321533203,
        32.35000228881836,
        32.590003967285156,
        35.56000518798828,
        39.95000457763672,
        53.840003967285156,
        56.20000457763672,
        57.95000457763672,
        59.29000473022461,
        59.77000427246094,
        59.920005798339844,
        61.190006256103516,
        61.96000671386719,
        62.50000762939453,
        63.3700065612793,
        63.48000717163086,
        63.48000717163086,
        63.66000747680664,
        63.850006103515625,
        64.08000946044922,
        64.760009765625,
        64.80001068115234,
        64.81001281738281,
        64.81001281738281
      ],
      "short_factor": [
        1.05,
        1.05,
        1.05,
        1.1,
        1.1,
        1.1500000000000001,
        1.2000000000000002,
        1.2500000000000002,
        1.3000000000000003,
        1.3500000000000003,
        1.5000000000000004,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.000000000000001,
        2.0500000000000007,
        2.0500000000000007,
        2.0500000000000007,
        2.1000000000000005,
        2.1000000000000005,
        2.1000000000000005,
        2.1500000000000004,
        2.1500000000000004,
        2.3499999999999996,
        2.549999999999999,
        2.5999999999999988,
        2.5999999999999988,
        2.7499999999999982,
        2.849999999999998,
        2.849999999999998,
        2.9499999999999975
      ],
      "type": "su"
    },
    "sliding_window": 262144,
    "torch_dtype": "bfloat16",
    "vocab_size": 32064
  },
  "text_model_id": "microsoft/Phi-3-mini-128k-instruct",
  "torch_dtype": "float32",
  "transformers_version": "4.41.2",
  "vocab_size": 32064
}