Update app.py

app.py

@@ -1,31 +1,22 @@
 import gradio as gr
-import transformers
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
-import torch
+from transformers import pipeline
 
-# Load the model and tokenizer from the Hugging Face Hub
-model = AutoModelForSequenceClassification.from_pretrained("preetidav/sentomodel")
-tokenizer = AutoTokenizer.from_pretrained("preetidav/sentomodel")
+# Load pre-trained model for CoLA (linguistic acceptability)
+model_name = "preetidav/distilbert-base-uncased-finetuned-cola"
+classifier = pipeline("text-classification", model=model_name)
 
-# Function to predict sentiment
-def predict_sentiment(text):
-    # Tokenize the input text
-    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
-    # Forward pass through the model
-    outputs = model(**inputs)
-    # Get the prediction (0 or 1 for binary classification)
-    prediction = torch.argmax(outputs.logits, dim=1).item()
-    # Map prediction to sentiment labels
-    return "positive" if prediction == 1 else "negative"
+def classify_sentence(sentence):
+    result = classifier(sentence)[0]
+    return f"Label: {result['label']} (Confidence: {result['score']:.2f})"
 
-# Set up the Gradio interface
+# Create Gradio interface
 iface = gr.Interface(
-    fn=predict_sentiment,              # Function to call
-    inputs=gr.Textbox(label="Input Text"),  # Input field for the text
-    outputs=gr.Textbox(label="Sentiment"), # Output field for the sentiment
-    title="Sentiment Analysis Model",    # Title of the app
-    description="This model predicts whether a given text has positive or negative sentiment.",  # Description of the app
+    fn=classify_sentence,
+    inputs=gr.Textbox(lines=2, placeholder="Enter a sentence..."),
+    outputs="text",
+    title="Sentence Acceptability Classifier",
+    description="This model classifies whether a sentence is linguistically acceptable (LABEL_1) or not (LABEL_0).",
 )
 
-# Launch the app
+# Launch app
 iface.launch()