add updated chat template example

README.md

@@ -7,6 +7,9 @@ license: apache-2.0
 # Model Card for Model ID
 Transformers compatible pixtral checkpoints. Make sure to install from source or wait for v4.45! 
 
+
+### Usage example
+
 ```python
 from PIL import Image
 from transformers import AutoProcessor, LlavaForConditionalGeneration
@@ -54,6 +57,8 @@ Each image captures a different scene, from a close-up of a dog to expansive nat
 """
 ```
 
+### Usage with chat template
+
 You can also use a chat template to format your chat history for Pixtral. Make sure that the `images` argument to the `processor` contains the images in the order
 that they appear in the chat, so that the model understands where each image is supposed to go.
 
@@ -86,6 +91,27 @@ generate_ids = model.generate(**inputs, max_new_tokens=500)
 output = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
 ```
 
+-----------
+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()`.
+
+```python
+chat = [
+    {
+      "role": "user", "content": [
+        {"type": "text", "content": "Can this animal"}, 
+        {"type": "image", "url": url_dog}, 
+        {"type": "text", "content": "live here?"}, 
+        {"type": "image", "url" : url_mountain}
+      ]
+    }
+]
+
+inputs = processor.apply_chat_template(chat, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors"pt").to(model.device)
+generate_ids = model.generate(**inputs, max_new_tokens=500)
+output = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+```
+
 You should get something like this:
 
 ```
@@ -108,4 +134,4 @@ Would you like more information on any specific aspect?
 ```
 
 While it may appear that spacing in the input is disrupted, this is caused by us skipping special tokens for display, and actually "Can this animal" and "live here" are
-correctly separated by image tokens. Try decoding with special tokens included to see exactly what the model sees!
+correctly separated by image tokens. Try decoding with special tokens included to see exactly what the model sees!