Update app.py

app.py

@@ -18,11 +18,9 @@ def load_model():
     tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, trust_remote_code=True)  # Use base model tokenizer
     base_model = AutoModelForCausalLM.from_pretrained(
         BASE_MODEL,
-        torch_dtype=torch.float16,
-        device_map="auto",
-        load_in_8bit=True
-    )
-    model = PeftModel.from_pretrained(base_model, FINETUNED_MODEL, device_map="auto")
+        torch_dtype=torch.float32,
+        device_map="cpu"    )
+    model = PeftModel.from_pretrained(base_model, FINETUNED_MODEL, device_map="cpu")
     return tokenizer, model
 
 # Load the model