Update README.md

README.md

@@ -23,7 +23,7 @@ It is a full finetune for one epoch.
 ## How to use:
 ```python
 import torch
-from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
 model_name = "timpal0l/Mistral-7B-v0.1-flashback-v2"
 device = "cuda:0" if torch.cuda.is_available() else "cpu"