config.json

{
  "architectures": [
    "DeSTA25AudioModel"
  ],
  "audio_locator": "<|AUDIO|>",
  "connector_mode": "qformer_1",
  "dtype": "bfloat16",
  "encoder_config": {
    "_name_or_path": "openai/whisper-large-v3-turbo",
    "activation_dropout": 0.0,
    "activation_function": "gelu",
    "apply_spec_augment": false,
    "architectures": [
      "WhisperForConditionalGeneration"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 50257,
    "classifier_proj_size": 256,
    "d_model": 1280,
    "decoder_attention_heads": 20,
    "decoder_ffn_dim": 5120,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 4,
    "decoder_start_token_id": 50258,
    "dropout": 0.0,
    "dtype": "float16",
    "encoder_attention_heads": 20,
    "encoder_ffn_dim": 5120,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 32,
    "eos_token_id": 50257,
    "init_std": 0.02,
    "mask_feature_length": 10,
    "mask_feature_min_masks": 0,
    "mask_feature_prob": 0.0,
    "mask_time_length": 10,
    "mask_time_min_masks": 2,
    "mask_time_prob": 0.05,
    "max_source_positions": 1500,
    "max_target_positions": 448,
    "median_filter_width": 7,
    "model_type": "whisper",
    "num_hidden_layers": 32,
    "num_mel_bins": 128,
    "pad_token_id": 50257,
    "scale_embedding": false,
    "use_cache": true,
    "use_weighted_layer_sum": false,
    "vocab_size": 51866
  },
  "encoder_model_id": "openai/whisper-large-v3-turbo",
  "eos_token_id": 151645,
  "info": "\uff24\uff45\uff53\uff54\uff41\uff12\u3002\uff15 \uff21\uff55\uff44\uff49\uff4f",
  "llm_config": {
    "_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
    "architectures": [
      "Qwen3ForCausalLM"
    ],
    "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": 2560,
    "initializer_range": 0.02,
    "intermediate_size": 9728,
    "layer_types": [
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 262144,
    "max_window_layers": 36,
    "model_type": "qwen3",
    "num_attention_heads": 32,
    "num_hidden_layers": 36,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 5000000,
    "sliding_window": null,
    "tie_word_embeddings": true,
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151936
  },
  "llm_model_id": "Qwen/Qwen3-4B-Instruct-2507",
  "model_type": "desta25",
  "pad_token_id": 151645,
  "placeholder_token": "<|video_pad|>",
  "prompt_size": 64,
  "qformer_num_hidden_layers": 6,
  "target_layer_ids": [
    7,
    15,
    23,
    31
  ],
  "train_id": 30678,
  "transformers_version": "4.57.3",
  "use_lora": false
}