Update app.py

app.py

@@ -31,7 +31,8 @@ if not torch.cuda.is_available():
 
 if torch.cuda.is_available():
     model_id = "meta-llama/Llama-2-7b-chat-hf"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+    auth_token = "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"
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", use_auth_token=auth_token)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False