fix: add correct ViT config (and handler)

config.json

@@ -1,29 +1,36 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "google/vit-base-patch16-224",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "ViTForImageClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
+  "id2label": {
+    "0": "stable_diffusion",
+    "1": "midjourney",
+    "2": "dalle",
+    "3": "real",
+    "4": "other_ai"
+  },
+  "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "label2id": {
+    "dalle": 2,
+    "midjourney": 1,
+    "other_ai": 4,
+    "real": 3,
+    "stable_diffusion": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
   "num_attention_heads": 12,
+  "num_channels": 3,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
+  "patch_size": 16,
+  "qkv_bias": true,
+  "transformers_version": "4.46.3"
 }