Upload ViT Base artifacts (weights + configs + preprocess)

README.md

@@ -1,3 +1,18 @@
----
-license: mit
----
+---
+license: apache-2.0
+tags:
+  - vision-transformer
+  - deepfake-detection
+  - image-classification
+---
+
+# ViT Base – DeepFakeDetector
+
+Vision Transformer (ViT-B/16) fine-tuned for binary deepfake detection.
+
+## Labels
+- 0 = real
+- 1 = fake
+
+## Output
+- prob_fake ∈ [0,1] (softmax or sigmoid)

config.json

@@ -0,0 +1,16 @@
+{
+  "name": "vit-base",
+  "framework": "pytorch",
+  "arch": "vit_base_patch16_224",
+  "patch_size": 16,
+  "hidden_dim": 768,
+  "num_layers": 12,
+  "num_heads": 12,
+  "num_classes": 2,
+  "threshold": 0.5,
+  "labels": {
+    "0": "real",
+    "1": "fake"
+  },
+  "notes": "ViT Base transfer learning model for deepfake detection"
+}

deepfake_vit_finetuned_wildfake.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da70e21817a0c591e09a11c0a3ebaac649671392f40721a50baefbf83e46cdb
+size 1034527103

label_map.json

@@ -0,0 +1,4 @@
+{
+  "0": "real",
+  "1": "fake"
+}

preprocess.json

@@ -0,0 +1,16 @@
+{
+  "input_size": 224,
+  "interpolation": "bicubic",
+  "normalize": {
+    "mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "std": [
+      0.229,
+      0.224,
+      0.225
+    ]
+  }
+}