Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+---
+base_model:
+- openai/clip-vit-large-patch14
+datasets:
+- svhn
+metrics:
+- accuracy
+---
+
+# Model Card
+
+## Model Details
+
+- Architecture: ViT-Large with patch size 14
+- Training Data: SVHN dataset
+
+## Training Details
+
+  Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=32).
+  Only the vision encoder is fine-tuned.
+
+## Evaluation Results
+
+- pre-trained: 0.6830110549926758
+- fine-tuned: 0.9790836572647095
+