Update README with new chat template example (#18)

- Update README.md (990cdb320db445f892a68db61e7223b1b3d060a1)


Co-authored-by: Raushan Turganbay <[email protected]>

README.md

@@ -118,6 +118,39 @@ response = processor.decode(output_ids, skip_special_tokens=True)
 print(response)
 ```
 
+-----------
+From transformers>=v4.48, you can also pass image url or local path to the conversation history, and let the chat template handle the rest.
+Chat template will load the image for you and return inputs in `torch.Tensor` which you can pass directly to `model.generate()`.
+
+Here is how to rewrite the above example
+
+```python
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"}
+            {"type": "text", "text": "what is the image?"},
+        ],
+    },
+]
+
+inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors"pt")
+ipnuts = inputs.to(model.device, torch.bfloat16)
+
+output = model.generate(
+    **inputs,
+    max_new_tokens=15,
+    stop_strings=["<|im_end|>"],
+    tokenizer=processor.tokenizer,
+    do_sample=True,
+    temperature=0.9,
+)
+output_ids = output[0][inputs["input_ids"].shape[1]:]
+response = processor.decode(output_ids, skip_special_tokens=True)
+print(response)
+```
+
 ### Advanced Inference and Fine-tuning
 We provide a [codebase](https://github.com/rhymes-ai/Aria) for more advanced usage of Aria,
 including vllm inference, cookbooks, and fine-tuning on custom datasets.