Update app.py

app.py

@@ -92,8 +92,10 @@ def generate(
     for user, assistant in chat_history:
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
     conversation.append({"role": "user", "content": make_prompt(message)})
-    enc = tokenizer(make_prompt(message), return_tensors="pt", padding=True, truncation=True)
-    input_ids = enc.input_ids.to(model.device)
+    # enc = tokenizer(make_prompt(message), return_tensors="pt", padding=True, truncation=True)
+    # input_ids = enc.input_ids.to(model.device)
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")