Update app.py

app.py

@@ -1,18 +1,39 @@
 import gradio as gr
 from transformers import pipeline
+from datasets import Dataset, DatasetDict
+import pandas as pd
+import numpy as np
+from transformers import RobertaTokenizerFast, RobertaForSequenceClassification,Trainer, TrainingArguments
 
-classifier = pipeline("text_classification", model="Prakhar618/Gptdetect")
+model = RobertaForSequenceClassification.from_pretrained('Prakhar618/Gptdetect')
+tokenizer = RobertaTokenizerFast.from_pretrained('Prakhar618/Gptdetect', max_length = 256)
 
 
 def predict(text):
     # Convert test dataframe to Hugging Face dataset
-    test_dataset = Dataset.from_pandas(text)
+    test_dataset = Dataset.from_pandas(pd.DataFrame(text,columns=['text']))
 
     # Apply the tokenization function to the train dataset
-    train_dataset = test_dataset.map(tokenize_function, batched=True,)
+    train_dataset1 = test_dataset.map(tokenize_function, batched=True,)
     predictions, label_probs, _ = trainer.predict(train_dataset1)
     y_pred = np.argmax(predictions, axis=1)
     return y_pred
+    
+
+def tokenize_function(examples):
+    return tokenizer(examples['text'], padding=True, truncation=True,
+        max_length=256)
+
+test_args = TrainingArguments(
+    do_train=False,
+    do_predict=True,
+    per_device_eval_batch_size = 2
+
+)
+trainer = Trainer(
+    model=model,
+    args=test_args,
+)
 
 iface = gr.Interface(fn=predict, inputs="text", outputs="text")
 iface.launch()