Updated README for GPU configuration.

README.md

@@ -109,6 +109,13 @@ model = Qwen2VLForConditionalGeneration.from_pretrained(
     "Qwen/Qwen2-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
 )
 
+# alternative if you are facing nan issues on output with  device_map="auto" settings.
+device = torch.device(f"cuda:xxx" if torch.cuda.is_available() else "cpu")
+# model = Qwen2VLForConditionalGeneration.from_pretrained(
+#    "Qwen/Qwen2-VL-7B-Instruct", torch_dtype=torch.bfloat16, device_map=device
+#)
+# model.eval()
+
 # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
 # model = Qwen2VLForConditionalGeneration.from_pretrained(
 #     "Qwen/Qwen2-VL-7B-Instruct",