Update app.py

app.py

@@ -61,8 +61,7 @@ def generate(
             
             ### Response:
             """
-    chat = tokenizer.apply_chat_template(prompt, tokenize=False)
-    inputs = tokenizer(chat, return_tensors="pt", add_special_tokens=False).to("cuda")
+    inputs = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cuda()
     if len(inputs) > MAX_INPUT_TOKEN_LENGTH:
         inputs = inputs[-MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning("Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")