Create app.py

app.py

@@ -0,0 +1,44 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load model and tokenizer
+model_name = "King-8/confidence-classifier"  # change to your actual model path
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+# Label mapping (update if yours are flipped)
+id2label = model.config.id2label
+
+label_map = {
+    "LABEL_0": "confident",
+    "LABEL_1": "not confident"
+}
+
+def classify_confidence(text):
+    # Tokenize input (exclude token_type_ids)
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+    if "token_type_ids" in inputs:
+        del inputs["token_type_ids"]
+
+    # Predict
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        probs = torch.nn.functional.softmax(logits, dim=1)
+        predicted_class = torch.argmax(probs).item()
+        prediction = label_map[predicted_class]
+        label = id2label[predicted_class]
+        score = round(probs[0][predicted_class].item() * 100, 2)
+
+    return f"{label} ({score}%)"
+
+iface = gr.Interface(
+    fn=classify_confidence,
+    inputs=gr.Textbox(lines=3, placeholder="Enter a statement..."),
+    outputs="text",
+    title="Confidence Classifier",
+    description="Enter a statement and the model will classify it as 'confident' or 'not confident'.",
+)
+
+iface.launch()