Update app.py

app.py

@@ -25,7 +25,7 @@ import requests
 import accelerate
 import bitsandbytes
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
+# device = "cuda" if torch.cuda.is_available() else "cpu"
 temperature=0.4
 max_new_tokens=240
 top_p=0.92
@@ -33,7 +33,7 @@ repetition_penalty=1.7
 
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
 model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
-    device_map=device,
+    device_map="auto",
     torch_dtype="auto"
 )
 model.eval()