Update app.py

app.py

@@ -13,7 +13,7 @@ print(dataset)
 tokenizer = AutoTokenizer.from_pretrained("allenai/scibert_scivocab_uncased")
 
 def tokenize_function(examples):
-    return tokenizer(examples["abstract"], padding="max_length", truncation=True)
+    return tokenizer(examples["abstract"], padding="max_length", truncation=True, max_length=151)
 
 dataset = dataset.map(tokenize_function, batched=True)
 
@@ -23,7 +23,7 @@ model = AutoModelForSequenceClassification.from_pretrained("allenai/scibert_sciv
 # Schritt 4: Trainingsparameter setzen
 training_args = TrainingArguments(
     output_dir="./results",
-    evaluation_strategy="epoch",
+    eval_strategy="epoch",
     per_device_train_batch_size=8,
     per_device_eval_batch_size=8,
     num_train_epochs=3,
@@ -48,7 +48,7 @@ tokenizer.save_pretrained("./trained_model")
 
 # Schritt 7: Modell für Gradio bereitstellen
 def predict(text):
-    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding="max_length", max_length=512)
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding="max_length", max_length=151)
     with torch.no_grad():
         outputs = model(**inputs)
     logits = outputs.logits