models/kandinsky-2-2-decoder/prior_image_encoder/config.json

{
  "_name_or_path": "C:\\Users\\edesa\\.cache\\huggingface\\hub\\models--kandinsky-community--kandinsky-2-2-prior\\snapshots\\9fc51ad5732afc5d031724219d22e6c42179c5a8\\image_encoder",
  "architectures": [
    "CLIPVisionModelWithProjection"
  ],
  "attention_dropout": 0.0,
  "dropout": 0.0,
  "hidden_act": "gelu",
  "hidden_size": 1664,
  "image_size": 224,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "layer_norm_eps": 1e-05,
  "model_type": "clip_vision_model",
  "num_attention_heads": 16,
  "num_channels": 3,
  "num_hidden_layers": 48,
  "patch_size": 14,
  "projection_dim": 1280,
  "torch_dtype": "float16",
  "transformers_version": "4.35.2"
}