configs/vision_config.json

{
    "attention_dropout": 0.0,
    "hidden_act": "quick_gelu",
    "hidden_size": 768,
    "image_size": 224,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 16,
    "projection_dim": 512,
    "intermediate_transformer_output": [4, 6, 8]
  }