Create README.md

README.md

@@ -0,0 +1,23 @@
+---
+datasets:
+- mnist
+metrics:
+- accuracy
+---
+
+# Model Card: tanganke/clip-vit-base-patch32_mnist
+
+## Model Details
+
+- Architecture: ViT-Base with patch size 32
+- Training Data: MNIST dataset
+
+## Training Details
+
+  Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training.
+  Only the vision encoder is fine-tuned.
+
+## Evaluation Results
+
+- pre-trained: 0.4759327471256256
+- fine-tuned: 0.9957262277603149