{
  "_name_or_path": "VITA-MLLM/VITA-1.5",
  "architectures": [
    "VITAQwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "audio_prompt_finetune": false,
  "audio_prompt_num": null,
  "audio_state_predictor_tuning": false,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "freeze_audio_encoder": true,
  "freeze_audio_encoder_adapter": false,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "image_aspect_ratio": "square",
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "mm_audio_encoder": "VITA-MLLM/VITA-1.5_AudioEnc",
  "mm_hidden_size": 4096,
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_vision_tower": "OpenGVLab/InternViT-300M-448px",
  "model_type": "vita-Qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 6200,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.2",
  "tune_audio_mlp_adapter": false,
  "tune_mm_mlp_adapter": false,
  "unfreeze_vision_tower": false,
  "use_cache": false,
  "use_mm_proj": true,
  "use_s2": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}