Update app.py

app.py

@@ -24,19 +24,17 @@ word_vectors = api.load("glove-wiki-gigaword-50")
 # Check for GPU and set the device accordingly
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-# Load GPT-3.5-turbo model and tokenizer from Hugging Face
-tokenizer_ai = AutoTokenizer.from_pretrained("Xenova/gpt-3.5-turbo")
-model_ai = AutoModel.from_pretrained("Xenova/gpt-3.5-turbo").to(device)
+# Load GPT-J-6B model and tokenizer from Hugging Face
+tokenizer_ai = AutoTokenizer.from_pretrained("EleutherAI/gpt-j-6B")
+model_ai = AutoModel.from_pretrained("EleutherAI/gpt-j-6B").to(device)
 
-# AI detection function using GPT-3.5-turbo-based model
+# AI detection function using GPT-J-6B-based model
 def detect_ai_generated(text):
     inputs = tokenizer_ai(text, return_tensors="pt", truncation=True, max_length=512).to(device)
     with torch.no_grad():
         outputs = model_ai(**inputs)
-        # Since this model does not directly output classification logits, you'll need to process the hidden states
-        # For simplicity, let's just use the first hidden state for now (you may need to adjust based on your use case)
+        # Process the hidden states to generate a score (example logic, adjust as needed)
         hidden_state = outputs.last_hidden_state[:, 0, :]  # Use the first token's representation
-        # Example: calculate some kind of score based on the hidden state
         score = torch.mean(hidden_state).item()
     return f"AI-Generated Content Score: {score:.2f}"