Upload README.md with huggingface_hub

README.md

@@ -64,22 +64,31 @@ embeddings = model.encode(["Hello world", "Hi there"])
 
 ### Interpretability
 
-Token-level attribution via Integrated Gradients (requires `pip install captum`):
+Token-level attribution via Integrated Gradients:
 
 ```python
 # Get raw token attributions
-result = model.interpret("The vaccine failed all trials.", "The vaccine was proven effective.")
+result = model.interpret("The cat sat on the mat.", "A feline rested on the rug.")
 for token, attr in zip(result["tokens"], result["attributions"]):
     print(f"{token:>15s}  {attr:+.4f}")
 
 # Save interactive HTML heatmap
 model.visualize(
-    "The vaccine failed all trials.",
-    "The vaccine was proven effective.",
+    "The cat sat on the mat.",
+    "A feline rested on the rug.",
+    label="Correct",
     output_path="attribution.html",
 )
 ```
 
+**Aligned pair** ("The cat sat on the mat." vs. "A feline rested on the rug."):
+
+![Attribution example - aligned](attrbution_ex1.jpeg)
+
+**Contradictory pair** ("It is raining outside." vs. "The weather is sunny and clear."):
+
+![Attribution example - contradictory](attrbution_ex2.jpeg)
+
 ## Evaluation Benchmarks
 
 Evaluated on 7 benchmarks: SNLI, MultiNLI, MedNLI, TruthfulQA, COCO-Caption, NEWTS, and Climate-FEVER.