{
  "_class_name": "Qwen3VLVisionModel",
  "deepstack_visual_indexes": [
    8,
    16,
    24
  ],
  "depth": 27,
  "dtype": "float16",
  "hidden_act": "gelu_pytorch_tanh",
  "hidden_size": 1152,
  "in_channels": 3,
  "initializer_range": 0.02,
  "intermediate_size": 4304,
  "model_type": "qwen3_vl_vision",
  "num_heads": 16,
  "num_position_embeddings": 2304,
  "out_hidden_size": 4096,
  "patch_size": 16,
  "spatial_merge_size": 2,
  "temporal_patch_size": 2,
  "transformers_version": "5.10.4"
}