Update llm.py

llm.py

@@ -5,7 +5,7 @@ import time
 
 class Gemma2B:
     def __init__(self):
-        self.model_name = "models/google/gemma-2b-it"
+        self.model_name = "google/gemma-2b-it"
         self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)
         self.model = AutoModelForCausalLM.from_pretrained(self.model_name, torch_dtype=torch.bfloat16, )