diff --git a/README.md b/README.md
index 4ba2136..9759cbf 100644
--- a/README.md
+++ b/README.md
@@ -15,7 +15,8 @@ language:
 - tr 
 - ur 
 - vu 
-- zh 
+- zh
+license: mit
 tags:
 - zero-shot-classification
 - text-classification
@@ -42,6 +43,7 @@ As of December 2021, mDeBERTa-base is the best performing multilingual base-size
 ```python
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
+device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
 
 model_name = "MoritzLaurer/mDeBERTa-v3-base-mnli-xnli"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -53,10 +55,8 @@ hypothesis = "Emmanuel Macron is the President of France"
 input = tokenizer(premise, hypothesis, truncation=True, return_tensors="pt")
 output = model(input["input_ids"].to(device))  # device = "cuda:0" or "cpu"
 prediction = torch.softmax(output["logits"][0], -1).tolist()
-
 label_names = ["entailment", "neutral", "contradiction"]
 prediction = {name: round(float(pred) * 100, 1) for pred, name in zip(prediction, label_names)}
-
 print(prediction)
 ```
 
@@ -87,7 +87,7 @@ average | ar | bg | de | el | en | es | fr | hi | ru | sw | th | tr | ur | vu |
 ## Limitations and bias
 Please consult the original DeBERTa-V3 paper and literature on different NLI datasets for potential biases. 
 
-## BibTeX entry and citation info
+## Citation
 If you use this model, please cite: Laurer, Moritz, Wouter van Atteveldt, Andreu Salleras Casas, and Kasper Welbers. 2022. ‘Less Annotating, More Classifying – Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT - NLI’. Preprint, June. Open Science Framework. https://osf.io/74b8k.
 
 ## Ideas for cooperation or questions?