Update README.md

README.md

@@ -10,3 +10,18 @@ tags:
 - legal
 ---
 pip install transformers datasets torch
+
+from datasets import load_dataset
+
+# Load the dataset (using an example dataset here; replace with your dataset)
+dataset = load_dataset('Hamses/EU_Regulation_261_2004')
+
+# Preprocess the dataset
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
+
+def preprocess_function(examples):
+    return tokenizer(examples['text'], padding='max_length', truncation=True)
+
+encoded_dataset = dataset.map(preprocess_function, batched=True)