Update app.py

app.py

@@ -153,17 +153,18 @@ def chat(user_text, model_label, blocks_json):
 
     messages = build_messages(user_text, data["user_profile"], blocks)
 
-    inputs = tokenizer.apply_chat_template(
-        messages,
-        add_generation_prompt=True,
-        tokenize=True,
-        return_tensors="pt"
+   inputs = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_tensors="pt",
+    return_dict=True   # <-- this makes inputs a dict
     ).to("cpu")
-
+    
     start = time.time()
     with torch.no_grad():
         outputs = model.generate(
-            **inputs,
+            **inputs,                # now safe, inputs is a dict
             max_new_tokens=200,
             do_sample=False,
             use_cache=False