Update app.py

app.py

@@ -21,7 +21,7 @@ model_name = "OpenLLM-France/Claire-7B-0.1"
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
 model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
     device_map="auto",
-    torch_dtype=torch.bfloat16
+    torch_dtype=torch.bfloat16,
     load_in_4bit=True                          # For efficient inference, if supported by the GPU card
 )
 model = model.to_bettertransformer()