Update app.py

app.py

@@ -62,3 +62,22 @@ demo = gr.ChatInterface(
 
 if __name__ == "__main__":
     demo.launch()
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base_model_name = "unsloth/qwen2.5-math-7b-bnb-4bit"
+peft_model_name = "Hrushi02/Root_Math"
+
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_name, 
+    torch_dtype=torch.float16, 
+    device_map="auto"
+)
+
+# Load PEFT model
+model = PeftModel.from_pretrained(base_model, peft_model_name)
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(base_model_name)