Update app.py

added the quantization_config back in

app.py

@@ -31,6 +31,13 @@ model = AutoModelForCausalLM.from_pretrained(
     quantization_config=quantization_config,
 )
 
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    trust_remote_code=True,
+    quantization_config=quantization_config,
+)
+
 model_path = "WhiteRabbitNeo/Trinity-13B"
 
 hf_token = os.getenv("HF_TOKEN")