{
  "_name_or_path": "Qwen/Qwen1.5-0.5B",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "image_aspect_ratio": "square",
  "image_projector_type": "mlp2x_gelu",
  "initializer_range": 0.02,
  "intermediate_size": 2816,
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "mm_hidden_size": 768,
  "mm_image_tower": "google/siglip-base-patch16-256-multilingual",
  "mm_projector_lr": null,
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_video_tower": null,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "model_type": "llava_qwen1_5",
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "num_key_value_heads": 16,
  "pad_token_id": 151646,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": true,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.37.0",
  "tune_mm_mlp_adapter": true,
  "use_cache": false,
  "use_mm_proj": true,
  "use_sliding_window": false,
  "video_global_proj": false,
  "video_projector_type": "linear",
  "video_spatial_proj": false,
  "video_temproal_proj": false,
  "vocab_size": 151936
}