first

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+
+# Load model and tokenizer
+model_name = "Kyudan/distilbert-base-uncased-finetuned-cola"
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+def classify_text(text):
+    # Tokenize the input text
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+
+    # Perform inference
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    # Get the predicted class and its probability
+    probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    predicted_class = torch.argmax(probabilities, dim=-1).item()
+    confidence = probabilities[0][predicted_class].item()
+
+    # Map the predicted class to a label (assuming binary classification)
+    label = "Positive" if predicted_class == 1 else "Negative"
+
+    return f"Classification: {label}\nConfidence: {confidence:.2f}"
+
+# Gradio interface setup
+demo = gr.Interface(
+    fn=classify_text,
+    inputs="text",
+    outputs="text",
+    title="Text Classification Demo",
+    description="Enter a sentence to classify its sentiment (positive/negative)."
+)
+
+if __name__ == "__main__":
+    demo.launch(share=True)

requirements.txt

@@ -0,0 +1,4 @@
+huggingface_hub==0.22.2
+datasets
+torch
+transformers