Update getans.py

getans.py

@@ -5,14 +5,11 @@ token1="hf_"
 token2="rPlNHzkJScHYmtGSaQPcaoKcjJGYQEpjLu"
 login(token=token1+token2)
 
-
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
 model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
 
-model.to(device)
-
 def get_response(prompt, max_new_tokens=50):
     inputs = tokenizer(prompt, return_tensors="pt")
     outputs = model.generate(**inputs, max_new_tokens=max_new_tokens, temperature=0.0001, do_sample=True)