Update README.md

README.md

@@ -55,12 +55,19 @@ from transformers import AutoModel, CLIPImageProcessor
 from transformers import AutoTokenizer
 
 path = "OpenGVLab/InternVL-Chat-Chinese-V1-1"
+# If your GPU has more than 40G memory, you can put the entire model on a single GPU.
 model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
-    trust_remote_code=True,
-    device_map='auto').eval()
+    trust_remote_code=True).eval().cuda()
+# Otherwise, you need to set device_map='auto' to use multiple GPUs for inference.
+# model = AutoModel.from_pretrained(
+#     path,
+#     torch_dtype=torch.bfloat16,
+#     low_cpu_mem_usage=True,
+#     trust_remote_code=True,
+#     device_map='auto').eval()
 
 tokenizer = AutoTokenizer.from_pretrained(path)
 image = Image.open('./examples/image2.jpg').convert('RGB')