Upload Dinov2ForImageClassification

config.json

@@ -1,10 +1,11 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224",
+  "_name_or_path": "facebook/dinov2-base",
+  "apply_layernorm": true,
   "architectures": [
-    "ViTForImageClassification"
+    "Dinov2ForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
+  "drop_path_rate": 0.0,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
@@ -110,9 +111,8 @@
     "98": "Tu-154",
     "99": "Yak-42"
   },
-  "image_size": 224,
+  "image_size": 518,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "707-320": 0,
     "727-200": 1,
@@ -215,14 +215,38 @@
     "Tu-154": 98,
     "Yak-42": 99
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
   "num_attention_heads": 12,
   "num_channels": 3,
   "num_hidden_layers": 12,
-  "patch_size": 16,
-  "problem_type": "single_label_classification",
+  "out_features": [
+    "stage12"
+  ],
+  "out_indices": [
+    12
+  ],
+  "patch_size": 14,
   "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12"
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.46.0"
+  "transformers_version": "4.46.0",
+  "use_swiglu_ffn": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b221d922526f99ea947cba30433fe0fb9d48515ace4ac22a10072b1397c0d94
-size 343525432
+oid sha256:375ae0adda802f8aeba1e51bde7a61099ec629564b46d4f0d72008b4d118c82a
+size 346962448