{
  "architectures": [
    "PvtV2Model"
  ],
  "attention_probs_dropout_prob": 0.1,
  "depths": [
    2,
    2,
    2,
    2
  ],
  "drop_path_rate": 0.0,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_sizes": [
    16,
    32,
    64,
    128
  ],
  "image_size": [
    64,
    64
  ],
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-06,
  "linear_attention": false,
  "mlp_ratios": [
    8,
    8,
    4,
    4
  ],
  "model_type": "pvt_v2",
  "num_attention_heads": [
    1,
    2,
    4,
    8
  ],
  "num_channels": 3,
  "num_encoder_blocks": 4,
  "out_features": [
    "stage1",
    "stage2",
    "stage3",
    "stage4"
  ],
  "out_indices": [
    0,
    1,
    2,
    3
  ],
  "patch_sizes": [
    7,
    3,
    3,
    3
  ],
  "qkv_bias": true,
  "sr_ratios": [
    8,
    4,
    2,
    1
  ],
  "stage_names": [
    "stage1",
    "stage2",
    "stage3",
    "stage4"
  ],
  "strides": [
    4,
    2,
    2,
    2
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.39.0.dev0"
}