Update app.py

app.py

@@ -20,8 +20,8 @@ raven_pipeline = pipeline(
 @spaces.GPU
 def process_text(input_text: str) -> str:
     prompt = f"User Query: {input_text}<human_end>"
-    result = raven_pipeline(prompt, max_new_tokens=2048, return_full_text=False, do_sample=False)[0]["generated_text"]
-    torch.cuda.empty_cache()
+    result = raven_pipeline(prompt, "stop" : ["<bot_end>"], max_new_tokens=2000, return_full_text=False, do_sample=False)[0]["generated_text"]
+#   torch.cuda.empty_cache()
     return result
 
 def create_interface():