Update app.py

app.py

@@ -20,11 +20,20 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID, token=HF_TOKEN)
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, token=HF_TOKEN)
-model.to(device)
+
+# ← changed from model.to(device)
+model = model.to_empty(device)
+
 model.eval()
 
 def classify(prompt: str):
-    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, padding=True, max_length=512).to(device)
+    inputs = tokenizer(
+        prompt,
+        return_tensors="pt",
+        truncation=True,
+        padding=True,
+        max_length=512
+    ).to(device)
     with torch.no_grad():
         logits = model(**inputs).logits
         probs = torch.softmax(logits, dim=-1).squeeze().cpu()