Updated README.md with pipeline example

Added this small snippet using transformers.Text2TextGenerationPipeline for ease of use.

README.md

@@ -38,6 +38,29 @@ This model is based on the T5-base model. We used "transfer learning" to get our
 
 [Author's LinkedIn](https://www.linkedin.com/in/vladimir-vorobev/) link
 
+## Using with pipeline
+```python
+from transformers import pipeline
+
+generator = pipeline(model="humarin/chatgpt_paraphraser_on_T5_base")
+```
+
+**Input**
+```python
+generator('What are the best places to see in New York?', num_return_sequences=5, do_sample=True)
+```
+**Output**
+```python
+[{'generated_text': 'Which locations in New York are worth visiting and why?'},
+ {'generated_text': 'Can you recommend any must-see sites in New York?'},
+ {'generated_text': 'Which Bostonian sites are considered the funniest to visit in New York?'},
+ {'generated_text': 'Which are the top destinations to discover in New York?'},
+ {'generated_text': 'What are some must-see attractions in New York?'}]
+```
+
+
+You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:
+
 ## Deploying example
 ```python
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM