Upload app.py with huggingface_hub

app.py

@@ -37,18 +37,22 @@ def generate_response(message, history_tuples=None):
             messages.append({"role": "assistant", "content": assistant_msg})
     messages.append({"role": "user", "content": message})
 
-    inputs = tokenizer.apply_chat_template(
+    input_ids = tokenizer.apply_chat_template(
         messages,
         add_generation_prompt=True,
         return_tensors="pt",
-    ).to(model.device)
+    )
+    # apply_chat_template may return a tensor or BatchEncoding depending on version
+    if hasattr(input_ids, "input_ids"):
+        input_ids = input_ids.input_ids
+    input_ids = input_ids.to(model.device)
 
-    input_tokens = inputs.shape[1]
+    input_tokens = input_ids.shape[1]
 
     start_time = time.time()
     with torch.no_grad():
         outputs = model.generate(
-            inputs,
+            input_ids,
             max_new_tokens=MODEL_CONFIG["max_new_tokens"],
             temperature=MODEL_CONFIG["temperature"],
             do_sample=True,