Update app.py

app.py

@@ -8,7 +8,7 @@ HF_TOKEN = os.environ.get("HF_TOKEN", None)
 
 # Load the tokenizer and model
 tokenizer = GemmaTokenizer.from_pretrained("google/codegemma-7b-it")
-model = AutoModelForCausalLM.from_pretrained("google/codegemma-7b-it").to("cuda:0")
+model = AutoModelForCausalLM.from_pretrained("google/codegemma-7b-it", device_map="auto") #.to("cuda:0")
 
 
 def codegemma(message: str, history: list, temperature: float, max_new_tokens: int) -> str: