Update app.py

app.py

@@ -140,7 +140,7 @@ class CustomDataset(torch.utils.data.Dataset):
                 text,
                 max_length=self.max_length,
                 padding='max_length',
-                truncation=True,
+                trunc ation=True,
                 return_attention_mask=True,
                 return_tensors='pt',
             )
@@ -154,7 +154,7 @@ class CustomDataset(torch.utils.data.Dataset):
             logger.error(f"Error in processing item {idx}: {e}")
             raise
 
-def train_model(model_name, data, batch_size, epochs, learning_rate=1e-5, max_length=512):
+def train_model(model_name, data, batch_size, epochs, learning_rate=1e-5, max_length=2048):
     try:
         model = AutoModelForSequenceClassification.from_pretrained(model_name)
         tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -266,7 +266,7 @@ iface = gr.Interface(
     fn=gradio_interface,
     inputs=[
         gr.Textbox(lines=5, label="Enter comma-separated URLs"),
-        gr.File(label="Upload file (including zip files)"),
+        gr.File(label="Upload file (including zip files)", type="file", max_size=1 * 1024 * 1024 * 1024),  # Allow files up to 1 GB
         gr.Textbox(lines=10, label="Enter or paste large text"),
         gr.Textbox(label="Model name", value="distilbert-base-uncased"),
         gr.Number(label="Batch size", value=8),