Update app.py

app.py

@@ -7,12 +7,12 @@ model_name = "allenai/scibert_scivocab_uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=3)  # z.B. für 3 Kategorien
 
-# 2️⃣ Dataset laden (ersetze mit deinem Dataset)
-dataset = load_dataset("scientific_papers", "arxiv")  # Hugging Face Datasets
+# 2️⃣ Dataset laden (armanc/scientific_papers)
+dataset = load_dataset("armanc/scientific_papers")
 
 # 3️⃣ Tokenisierung der Texte
 def tokenize_function(examples):
-    return tokenizer(examples["abstract"], padding="max_length", truncation=True)
+    return tokenizer(examples["text"], padding="max_length", truncation=True)
 
 tokenized_datasets = dataset.map(tokenize_function, batched=True)