Upload ViTForImageClassification (#1)

- Upload ViTForImageClassification (8afc0ec822088fa52ffd1bd502b66f11317b5442)

config.json

@@ -1,29 +1,26 @@
-{  
+{
   "architectures": [
     "ViTForImageClassification"
   ],
-  "model": {
-    
-    "variant": "vit_small_patch16_384.augreg_in21k_ft_in1k",
-    "input_size": 384,
-    "patch_size": 16,
-    "freeze_backbone": false,
-    "hidden_dropout_prob": 0.0,
-    "attention_probs_dropout_prob": 0.0,
-    "num_classes": 1,
-    "head": {
-      "in_features": 384,
-      "out_features": 1,
-      "bias": true
-    }
-  },
-  "preprocessing": {
-    "norm_mean": [0.48145466, 0.4578275, 0.40821073],
-    "norm_std": [0.26862954, 0.26130258, 0.27577711],
-    "resize_size": 440,
-    "crop_size": 384
-  },
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 384,
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-06,
+  "mlp_ratio": 4,
   "model_type": "vit",
-  "dtype": "float32",
-  "checkpoint_path": "pretrained_weights/model_v11_ViT_384_base_ckpt.pt"
-}
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_classes": 1,
+  "num_heads": 6,
+  "num_hidden_layers": 12,
+  "num_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0.dev0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f1eae65e18b00c41cf9a5442319bd4abd1e6347a5488c64dbff4164c96a3334
-size 87859824
+oid sha256:91a3c4d1b7d453b4b74e377c8e079662a6cc2c97f8ca448daedda8864ec54605
+size 143969256