App.py

# Your model repo
model_id = "globalbrandon/autotrainfriday1"

# Load pipeline (auto-detects type based on model)
classifier = pipeline("text-classification", model=model_id)

# Define prediction function
def predict(text):
try:
result = classifier(text)[0]
label = result["label"]
score = round(result["score"] * 100, 2)
return f"Prediction: {label} ({score}%)"
except Exception as e:
return f"Error: {str(e)}"

# Gradio interface
demo = gr.Interface(
fn=predict,
inputs=gr.Textbox(lines=4, placeholder="Enter your text here..."),
outputs=gr.Textbox(label="Model Prediction"),
title="Text Classifier",
description="This app uses a Hugging Face AutoTrain model to classify text."
)

demo.launch()

App.py

@@ -0,0 +1,27 @@
+# Your model repo
+model_id = "Meylai/ai-model-tryout"
+
+# Load pipeline (auto-detects type based on model)
+classifier = pipeline("text-classification", model=model_id)
+
+# Define prediction function
+def predict(text):
+    try:
+        result = classifier(text)[0]
+        label = result["label"]
+        score = round(result["score"] * 100, 2)
+        return f"Prediction: {label} ({score}%)"
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Gradio interface
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Textbox(lines=4, placeholder="Enter your text here..."),
+    outputs=gr.Textbox(label="Model Prediction"),
+    title="Text Classifier",
+    description="This app uses a Hugging Face AutoTrain model to classify text."
+)
+
+demo.launch()
+