Update app.py

app.py

@@ -60,12 +60,11 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 # # torch_dtype =torch.float16
 # model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_9",config=config, ignore_mismatched_sizes=True).to('cuda')
 # Load model directly
-@spaces.GPU(duration=300)
 
 tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini_00")
 model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_00", load_in_4bit=True).to('cuda')
 
-
+@spaces.GPU(duration=300)
 def chunk_it(input_command):
     alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.