Upload fine-tuned ViT

config.json

@@ -1,21 +1,12 @@
 {
   "architectures": [
-    "ConvNextForImageClassification"
+    "ViTForImageClassification"
   ],
-  "depths": [
-    3,
-    3,
-    9,
-    3
-  ],
-  "drop_path_rate": 0.0,
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
   "hidden_act": "gelu",
-  "hidden_sizes": [
-    96,
-    192,
-    384,
-    768
-  ],
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
   "id2label": {
     "0": "pizza",
     "1": "hamburger",
@@ -30,6 +21,7 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "caesar_salad": 3,
     "chocolate_cake": 9,
@@ -43,24 +35,15 @@
     "tacos": 7
   },
   "layer_norm_eps": 1e-12,
-  "layer_scale_init_value": 1e-06,
-  "model_type": "convnext",
+  "model_type": "vit",
+  "num_attention_heads": 12,
   "num_channels": 3,
-  "num_stages": 4,
-  "out_features": [
-    "stage4"
-  ],
-  "out_indices": [
-    4
-  ],
-  "patch_size": 4,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4"
-  ],
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f31edfeb2971c45dfc787356ac2dc8b818b7e0ade443d688df7b978365709ead
-size 111332552
+oid sha256:7ded3c6bcdc433f3ad62dd15e0f1f262be53ffaae051f21d666607407c06f672
+size 343248584