nit

README.md

@@ -39,17 +39,18 @@ The model supports multi-image and multi-prompt generation. Meaning that you can
 Below we used [`"llava-hf/llava-interleave-qwen-0.5b-hf"`](https://huggingface.co/llava-hf/llava-interleave-qwen-0.5b-hf) checkpoint.
 
 ```python
-from transformers import pipeline
+from transformers import pipeline, AutoProcessor
 from PIL import Image    
 import requests
 
 model_id = "llava-hf/llava-interleave-qwen-7b-dpo-hf"
 pipe = pipeline("image-to-text", model=model_id)
+processor = AutoProcessor.from_pretrained(model_id)
 
 url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"
 image = Image.open(requests.get(url, stream=True).raw)
 
-# Define a chat histiry and use `apply_chat_template` to get correctly formatted prompt
+# Define a chat history and use `apply_chat_template` to get correctly formatted prompt
 # Each value in "content" has to be a list of dicts with types ("text", "image") 
 conversation = [
     {
@@ -87,7 +88,7 @@ model = LlavaForConditionalGeneration.from_pretrained(
 
 processor = AutoProcessor.from_pretrained(model_id)
 
-# Define a chat histiry and use `apply_chat_template` to get correctly formatted prompt
+# Define a chat history and use `apply_chat_template` to get correctly formatted prompt
 # Each value in "content" has to be a list of dicts with types ("text", "image") 
 conversation = [
     {