Update app.py

app.py

@@ -21,6 +21,7 @@ model = AutoModelForCausalLM.from_pretrained(
 ).to(device)
 @spaces.GPU(enable_queue=True)
 def generate_text(text, temperature, maxLen):
+    text = text.strip().strip('<s>').strip()
     inputs = tokenizer([text], return_tensors="pt").to(device)
     streamer = TextIteratorStreamer(tokenizer)
     generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=maxLen, temperature=temperature)