Update app.py

app.py

@@ -392,8 +392,8 @@ if __name__ == '__main__':
         bnb_4bit_compute_dtype=torch.bfloat16
     )
 
-    tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", use_auth_token=HF_TOKEN)
-    model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", quantization_config=quantization_config, torch_dtype=torch.float16, low_cpu_mem_usage=True, use_auth_token=HF_TOKEN)
+    tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", token=HF_TOKEN)
+    model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", quantization_config=quantization_config, torch_dtype=torch.float16, low_cpu_mem_usage=True, token=HF_TOKEN)
 
 
     def make_inference(query, hist):