Create app.py

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+from transformers import BertConfig, BertForSequenceClassification, AutoTokenizer
+from safetensors import safe_open
+import torch
+
+config_path = "modelbert2/config.json"
+config = BertConfig.from_json_file(config_path)
+model = BertForSequenceClassification(config)
+
+
+model_path = "modelbert2"
+model = BertForSequenceClassification.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+tokenizer = AutoTokenizer.from_pretrained("modelbert2/")
+
+# Load the label encoder
+import pickle
+with open('label_encoder.pkl', 'rb') as file:
+    label_encoder = pickle.load(file)
+
+def predict(text):
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    predicted_class = torch.argmax(probs, dim=-1).item()
+    predicted_label = label_encoder.inverse_transform([predicted_class])[0]
+    return predicted_label
+
+
+# Define the markdown text with bullet points
+markdown_text = """
+- This is for test purpose only. 
+- Input one budget line per time. 
+- Accuracy of the model is around 72%.
+"""
+
+# Define the interface
+iface = gr.Interface(
+    fn=predict, 
+    inputs=gr.inputs.Textbox(lines=1, placeholder="Enter Budget line here..."), 
+    outputs="text", 
+    title="COFOG Level 1 Classification",
+    description=markdown_text  # Add the markdown text to the description
+)
+
+# Run the interface
+if __name__ == "__main__":
+    iface.launch()