Update app.py

app.py

@@ -53,7 +53,7 @@ input_text = st.text_input("Enter Text:", "Hello, how are you?")
 tokens = tokenizer.tokenize(input_text)
 st.write("Tokenized Output:", tokens)
 
-# Token Embeddings Visualization (PCA Projection)
+# Token Embeddings Visualization (Fixed PCA Projection)
 st.subheader("🧩 Token Embeddings Visualization")
 with torch.no_grad():
     inputs = tokenizer(input_text, return_tensors="pt")
@@ -61,6 +61,12 @@ with torch.no_grad():
 
     if hasattr(outputs, "last_hidden_state"):
         embeddings = outputs.last_hidden_state.squeeze(0).numpy()
+
+        # Ensure the number of tokens and embeddings match
+        n_tokens = min(len(tokens), embeddings.shape[0])
+        embeddings = embeddings[:n_tokens]  # Trim embeddings to match token count
+        tokens = tokens[:n_tokens]  # Trim tokens to match embeddings count
+
         pca = PCA(n_components=2)
         reduced_embeddings = pca.fit_transform(embeddings)