feat: add multiple images (or in-context learning) conversation examples (#47)

Co-authored-by: Bo Liu <benjaminliu.eecs@gmail.com>

README.md

@@ -132,18 +132,34 @@ tokenizer = vl_chat_processor.tokenizer
 vl_gpt: MultiModalityCausalLM = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)
 vl_gpt = vl_gpt.to(torch.bfloat16).cuda().eval()
 
+## single image conversation example
 conversation = [
     {
         "role": "User",
         "content": "<image_placeholder>Describe each stage of this image.",
-        "images": ["./images/training_pipelines.jpg"]
+        "images": ["./images/training_pipelines.jpg"],
     },
-    {
-        "role": "Assistant",
-        "content": ""
-    }
+    {"role": "Assistant", "content": ""},
 ]
 
+## multiple images (or in-context learning) conversation example
+# conversation = [
+#     {
+#         "role": "User",
+#         "content": "<image_placeholder>A dog wearing nothing in the foreground, "
+#                    "<image_placeholder>a dog wearing a santa hat, "
+#                    "<image_placeholder>a dog wearing a wizard outfit, and "
+#                    "<image_placeholder>what's the dog wearing?",
+#         "images": [
+#             "images/dog_a.png",
+#             "images/dog_b.png",
+#             "images/dog_c.png",
+#             "images/dog_d.png",
+#         ],
+#     },
+#     {"role": "Assistant", "content": ""}
+# ]
+
 # load images and prepare for inputs
 pil_images = load_pil_images(conversation)
 prepare_inputs = vl_chat_processor(