reduced max_new_tokens

app.py

@@ -22,7 +22,7 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype=torch.bfloat16,
     token=access_token
 )
-pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=2048)
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512)
 
 # Define functions for fetching stock data, news, and moving averages
 def validate_ticker(ticker):