Update app.py

app.py

@@ -1,12 +1,22 @@
 import torch
 from transformers import BertForSequenceClassification
+import gradio as gr
+from transformers import BertTokenizer
+import torch
+from transformers import BertForSequenceClassification, BertTokenizer
+import gradio as gr
 
 # Load your BERT model
+# Load the model architecture
 model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)
-model.load_state_dict(torch.load('bert_model_complete.pth', map_location=torch.device('cpu'), weights_only=True), strict=False)
+
+# Load the state dict without weights_only
+try:
+    model.load_state_dict(torch.load('bert_model_complete.pth', map_location=torch.device('cpu')), strict=False)
+except Exception as e:
+    print(f"Error loading state dict: {e}")
 model.eval()  # Set the model to evaluation mode
-import gradio as gr
-from transformers import BertTokenizer
+
 
 # Load the tokenizer
 tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
@@ -21,9 +31,6 @@ def predict(text):
 
 # Set up the Gradio interface
 interface = gr.Interface(fn=predict, inputs="text", outputs="label", title="BERT Text Classification")
-import torch
-from transformers import BertForSequenceClassification, BertTokenizer
-import gradio as gr
 
 # Load model and tokenizer
 model = BertForSequenceClassification.from_pretrained('bert-base-uncased')