Update app.py

app.py

@@ -36,20 +36,14 @@ def load_model(model_type):
         device = "cpu"  # Force CPU usage
         
         if model_type == "summarize":
-            base_model = AutoModelForSeq2SeqLM.from_pretrained(
-                "facebook/bart-large-cnn",
+            model = AutoModelForSeq2SeqLM.from_pretrained(
+                "pendar02/bart-large-pubmedd",
                 cache_dir="./models",
                 torch_dtype=torch.float32
             ).to(device)
             
-            model = PeftModel.from_pretrained(
-                base_model, 
-                "pendar02/results",
-                is_trainable=False
-            ).to(device)
-            
             tokenizer = AutoTokenizer.from_pretrained(
-                "facebook/bart-large-cnn",
+                "pendar02/bart-large-pubmedd",
                 cache_dir="./models"
             )
         else:  # question_focused