config.json

{
  "auto_map": {
    "AutoConfig": "configuration_phi4_multimodal.Phi4MultimodalConfig",
    "AutoModelForCausalLM": "modeling_phi4_multimodal.Phi4MultimodalForCausalLM"
  },
  "architectures": [
    "Phi4MultimodalForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "audio_config": {
    "activation": "swish",
    "audio_token_id": 200011,
    "bias_max_distance": 500,
    "bias_symmetric": false,
    "chunk_size": -1,
    "conv_activation": "swish",
    "conv_glu_type": "swish",
    "depthwise_multiplier": 1,
    "depthwise_seperable_out_channel": 1024,
    "downsample_rate": 1,
    "dropout_rate": 0.0,
    "ext_pw_out_channel": 1024,
    "feature_layer": -2,
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "input_size": 80,
    "intermediate_size": 1536,
    "kernel_size": 3,
    "left_chunk": 18,
    "model_type": "phi4_multimodal_audio",
    "nemo_activation": "relu",
    "nemo_conv_channels": 1024,
    "nemo_final_size": 10,
    "num_attention_heads": 16,
    "num_blocks": 24,
    "time_reduction": 8
  },
  "bos_token_id": 199999,
  "embd_pdrop": 0.0,
  "eos_token_id": [
    199999,
    200020
  ],
  "full_attn_mod": 1,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "interpolate_factor": 1,
  "lm_head_bias": false,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "phi4_multimodal",
  "num_attention_heads": 24,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "original_max_position_embeddings": 4096,
  "pad_token_id": 199999,
  "partial_rotary_factor": 0.75,
  "resid_pdrop": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "long_factor": [
      1,
      1.118320672,
      1.250641126,
      1.398617824,
      1.564103225,
      1.74916897,
      1.956131817,
      2.187582649,
      2.446418898,
      2.735880826,
      3.059592084,
      3.421605075,
      3.826451687,
      4.279200023,
      4.785517845,
      5.351743533,
      5.984965424,
      6.693110555,
      7.485043894,
      8.370679318,
      9.36110372,
      10.4687158,
      11.70738129,
      13.09260651,
      14.64173252,
      16.37415215,
      18.31155283,
      20.47818807,
      22.90118105,
      25.61086418,
      28.64115884,
      32.03,
      32.1,
      32.13,
      32.23,
      32.6,
      32.61,
      32.64,
      32.66,
      32.7,
      32.71,
      32.93,
      32.97,
      33.28,
      33.49,
      33.5,
      44.16,
      47.77
    ],
    "short_factor": [
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0
    ],
    "type": "longrope"
  },
  "rope_theta": 10000.0,
  "sliding_window": 262144,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.0.dev0",
  "use_cache": true,
  "vision_config": {
    "attention_dropout": 0.0,
    "crop_size": 448,
    "feature_layer": -2,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 448,
    "image_token_id": 200010,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "phi4_multimodal_vision",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "patch_size": 14
  },
  "vocab_size": 200064
}