{
  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
  "architectures": [
    "MobileVideoGPTQwenForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 896,
  "image_aspect_ratio": "pad",
  "image_grid_pinpoints": null,
  "image_mm_hidden_size": 768,
  "image_mm_projector_type": "etp",
  "image_mm_vision_tower": "openai/clip-vit-base-patch16",
  "initializer_range": 0.02,
  "intermediate_size": 4864,
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "mm_hidden_size": 768,
  "mm_projector_lr": 2e-05,
  "mm_projector_type": "etp",
  "mm_use_box_start_end": false,
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "OpenGVLab/VideoMamba/videomamba_m16_25M_f8_res224.pth",
  "model_type": "MobileVideoGPT_qwen",
  "num_attention_heads": 14,
  "num_hidden_layers": 24,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": true,
  "torch_dtype": "float16",
  "transformers_version": "4.42.4",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_mm_proj": true,
  "use_sliding_window": false,
  "vocab_size": 151666
}