image_encoder/config.json

{
  "architectures": [
    "CLIPVisionModel"
  ],
  "attention_dropout": 0.0,
  "dropout": 0.0,
  "dtype": "bfloat16",
  "hidden_act": "gelu",
  "hidden_size": 1280,
  "image_size": 224,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "intermediate_size": 5120,
  "layer_norm_eps": 1e-05,
  "model_type": "clip_vision_model",
  "num_attention_heads": 16,
  "num_channels": 3,
  "num_hidden_layers": 32,
  "patch_size": 14,
  "projection_dim": 1024,
  "transformers_version": "4.57.0"
}