{
  "architectures": [
    "EdgeInstantForConditionalGeneration"
  ],
  "audio_config": {
    "activation_dropout": 0,
    "activation_function": "gelu",
    "add_cross_attention": false,
    "attention_dropout": 0,
    "bos_token_id": null,
    "conv_chunksize": 500,
    "cross_attention_hidden_size": null,
    "d_model": 1024,
    "decoder_start_token_id": null,
    "downsample_hidden_size": 480,
    "dropout": 0,
    "dtype": "bfloat16",
    "encoder_attention_heads": 16,
    "encoder_ffn_dim": 4096,
    "encoder_layers": 24,
    "eos_token_id": null,
    "finetuning_task": null,
    "initializer_range": 0.02,
    "is_decoder": false,
    "max_source_positions": 1500,
    "model_type": "qwen3_omni_moe_audio_encoder",
    "n_window": 50,
    "n_window_infer": 800,
    "num_mel_bins": 128,
    "output_dim": 2048,
    "pad_token_id": null,
    "prefix": null,
    "pruned_heads": {},
    "scale_embedding": false,
    "sep_token_id": null,
    "task_specific_params": null,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "torchscript": false,
    "use_bfloat16": false
  },
  "audio_lora_config": null,
  "audio_pad_id": 248076,
  "audio_pool": 1,
  "audio_special_ids": [
    248070,
    248071,
    248076
  ],
  "audio_stack": 1,
  "audio_tap": "proj2",
  "auto_map": {
    "AutoConfig": "configuration_edgeinstant.EdgeInstantConfig",
    "AutoModel": "modeling_edgeinstant.EdgeInstantForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_edgeinstant.EdgeInstantForConditionalGeneration",
    "AutoProcessor": "processing_edgeinstant.EdgeInstantProcessor"
  },
  "bos_token_id": null,
  "codec_config": {},
  "dtype": "bfloat16",
  "eos_token_id": [
    248046,
    248046
  ],
  "max_audio_seconds": null,
  "model_type": "edgeinstant",
  "output_sampling_rate": 24000,
  "pad_token_id": 248044,
  "processor_class": "EdgeInstantProcessor",
  "projector_config": {
    "align_mode": "mlp",
    "audio_out_norm": false,
    "input_size": 2048,
    "intermediate_size": 16384,
    "norm_size": 2048,
    "output_size": 2048
  },
  "qa_prompt": "Listen to the user's speech and answer.",
  "sampling_rate": 16000,
  "talker_config": {},
  "think_end_id": 248069,
  "think_start_id": 248068,
  "thinker_config": {
    "architectures": [
      "Qwen3_5ForConditionalGeneration"
    ],
    "dtype": "bfloat16",
    "image_token_id": 248056,
    "model_type": "qwen3_5",
    "text_config": {
      "_name_or_path": "",
      "architectures": null,
      "attention_bias": false,
      "attention_dropout": 0.0,
      "attn_output_gate": true,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "dtype": "bfloat16",
      "eos_token_id": 248044,
      "full_attention_interval": 4,
      "head_dim": 256,
      "hidden_act": "silu",
      "hidden_size": 2048,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "initializer_range": 0.02,
      "intermediate_size": 6144,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_types": [
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention"
      ],
      "linear_conv_kernel_dim": 4,
      "linear_key_head_dim": 128,
      "linear_num_key_heads": 16,
      "linear_num_value_heads": 16,
      "linear_value_head_dim": 128,
      "mamba_ssm_dtype": "float32",
      "max_position_embeddings": 262144,
      "mlp_only_layers": [],
      "model_type": "qwen3_5_text",
      "mtp_num_hidden_layers": 1,
      "mtp_use_dedicated_embeddings": false,
      "num_attention_heads": 8,
      "num_hidden_layers": 24,
      "num_key_value_heads": 2,
      "output_attentions": false,
      "output_hidden_states": false,
      "pad_token_id": null,
      "partial_rotary_factor": 0.25,
      "problem_type": null,
      "return_dict": true,
      "rms_norm_eps": 1e-06,
      "rope_parameters": {
        "mrope_interleaved": true,
        "mrope_section": [
          11,
          11,
          10
        ],
        "partial_rotary_factor": 0.25,
        "rope_theta": 10000000,
        "rope_type": "default"
      },
      "tie_word_embeddings": true,
      "use_cache": true,
      "vocab_size": 248320
    },
    "tie_word_embeddings": true,
    "video_token_id": 248057,
    "vision_config": {
      "_name_or_path": "",
      "architectures": null,
      "chunk_size_feed_forward": 0,
      "deepstack_visual_indexes": [],
      "depth": 24,
      "dtype": "bfloat16",
      "hidden_act": "gelu_pytorch_tanh",
      "hidden_size": 1024,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "in_channels": 3,
      "initializer_range": 0.02,
      "intermediate_size": 4096,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "model_type": "qwen3_5_vision",
      "num_heads": 16,
      "num_position_embeddings": 2304,
      "out_hidden_size": 2048,
      "output_attentions": false,
      "output_hidden_states": false,
      "patch_size": 16,
      "problem_type": null,
      "return_dict": true,
      "spatial_merge_size": 2,
      "temporal_patch_size": 2
    },
    "vision_end_token_id": 248054,
    "vision_start_token_id": 248053
  },
  "thinker_special_ids": [
    248046,
    248044,
    248070,
    248071,
    248076,
    248056,
    248057,
    248053,
    248054
  ],
  "tie_word_embeddings": true,
  "transformers_version": "5.12.1"
}