Update README.md

cc

@ArthurZ



@sasha

README.md

@@ -55,8 +55,8 @@ You can use this model directly with a pipeline for text generation.
 >>> from transformers import pipeline
 
 >>> generator = pipeline('text-generation', model="facebook/opt-350m")
->>> generator("Hello, I'm am conscious and")
-[{'generated_text': "Hello, I'm am conscious and I'm a bit of a noob. I'm looking for"}]
+>>> generator("What are we having for dinner?")
+[{'generated_text': "What are we having for dinner?\nI'm having a steak and a salad.\nI'm""}]
 ```
 
 By default, generation is deterministic. In order to use the top-k sampling, please set `do_sample` to `True`. 
@@ -66,8 +66,8 @@ By default, generation is deterministic. In order to use the top-k sampling, ple
 
 >>> set_seed(32)
 >>> generator = pipeline('text-generation', model="facebook/opt-350m", do_sample=True)
->>> generator("Hello, I'm am conscious and")
-[{'generated_text': "Hello, I'm am conscious and I'm interested in this project. Can I get an initial contact"}]
+>>> generator("What are we having for dinner?")
+[{'generated_text': "What are we having for dinner?\n\nWith spring fast approaching, it’s only appropriate"}]
 ```
 
 ### Limitations and bias