Update README.md

README.md

@@ -34,15 +34,6 @@ df_sampled_code['input_ids'] = tokenizer(df_sampled_code['prompt'].tolist())['in
 
 ```
 
-or with a `pipeline`:
-
-```Python
-from transformers import pipeline
-
-pipe = pipeline("text-generation", model="codeparrot/codeparrot-small")
-outputs = pipe("def hello_world():")
-```
-
 ## Training
 
 The model was trained on the cleaned [CodeParrot 🦜 dataset](https://huggingface.co/datasets/codeparrot/codeparrot-clean) with the following settings: