{
  "architectures": [
    "GlmImageVisionModel"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "depth": 2,
  "dtype": "float32",
  "hidden_act": "gelu",
  "hidden_size": 32,
  "image_size": 128,
  "in_channels": 3,
  "initializer_range": 0.02,
  "intermediate_size": 22,
  "layer_norm_eps": 1e-06,
  "model_type": "glm_image_vision",
  "num_heads": 16,
  "patch_size": 16,
  "spatial_merge_size": 1,
  "temporal_patch_size": 1,
  "transformers_version": "5.16.0.dev0"
}