Update app.py

app.py

@@ -78,7 +78,7 @@ model = AutoModelForCausalLM.from_pretrained(
     "m-a-p/YuE-s1-7B-anneal-en-cot",
     torch_dtype=torch.bfloat16,
     attn_implementation="flash_attention_2",
-    quantization_config=quantization_config,
+    # quantization_config=quantization_config,
     low_cpu_mem_usage=True,
     # device_map="auto"     
 ).to(device)