Update app.py

app.py

@@ -21,6 +21,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id,
                                              # load_in_8bit=True,
                                              # quantization_config=nf4_config
+                                             torch_dtype = torch.bfloat16
                                             )
 
 @spaces.GPU