{
  "apply_audio_downsample": false,
  "architectures": [
    "ValleyOmniForConditionalGeneration"
  ],
  "audio_config": {
    "_name_or_path": "",
    "activation_dropout": 0,
    "activation_function": "gelu",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "conv_chunksize": 500,
    "cross_attention_hidden_size": null,
    "d_model": 1280,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "downsample_hidden_size": 480,
    "dropout": 0,
    "dtype": null,
    "early_stopping": false,
    "encoder_attention_heads": 20,
    "encoder_ffn_dim": 5120,
    "encoder_layers": 32,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_source_positions": 1500,
    "min_length": 0,
    "model_type": "qwen3_omni_moe_audio_encoder",
    "n_window": 50,
    "n_window_infer": 800,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 32,
    "num_mel_bins": 128,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_dim": 2048,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "scale_embedding": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false
  },
  "audio_encoder_type": "qwen3_omni_moe",
  "audio_end_token_id": 151670,
  "audio_start_token_id": 151669,
  "audio_token_id": 151675,
  "connector_hidden_size": 8192,
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "feature_dim": 128,
  "hidden_size": 5120,
  "image_token_id": 151655,
  "keys_to_ignore_at_inference": [
    "past_key_values",
    "hidden_states",
    "attention_mask"
  ],
  "model_type": "valley_omni",
  "pad_token_id": 151643,
  "position_id_per_seconds": 25,
  "rope_parameters": {
    "rope_theta": 5000000.0,
    "rope_type": "default"
  },
  "sample_rate": 16000,
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "dtype": "bfloat16",
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 25600,
    "max_position_embeddings": 262144,
    "model_type": "qwen3_vl_text",
    "num_attention_heads": 64,
    "num_hidden_layers": 64,
    "num_key_value_heads": 8,
    "pad_token_id": 151643,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "mrope_interleaved": true,
      "mrope_section": [
        24,
        20,
        20
      ],
      "rope_theta": 5000000,
      "rope_type": "default"
    },
    "rope_theta": 5000000,
    "use_cache": true,
    "vocab_size": 151936
  },
  "tie_word_embeddings": false,
  "tm_rope_sections": [
    24,
    20,
    20
  ],
  "transformers_version": "5.0.0.dev0",
  "use_cache": true,
  "video_token_id": 151656,
  "vision_config": {
    "deepstack_visual_indexes": [
      8,
      16,
      24
    ],
    "depth": 27,
    "dtype": "bfloat16",
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 4304,
    "model_type": "qwen3_vl",
    "num_heads": 16,
    "num_position_embeddings": 2304,
    "out_hidden_size": 5120,
    "pad_token_id": 151643,
    "patch_size": 16,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652,
  "vocab_size": 151936
}