Update app.py

app.py

@@ -1,12 +1,32 @@
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
 import gradio as gr
+from peft import PeftModel, PeftConfig
 import spaces
 
-
 # Use the GPU if available
 device = 0 if torch.cuda.is_available() else -1
-pipe = pipeline("text-generation", model="ombhojane/smile-small", device=device)
+
+def load_model():
+    # Load the base model and tokenizer
+    base_model_name = "Qwen/Qwen2.5-1.5B-Instruct"
+    tokenizer = AutoTokenizer.from_pretrained(base_model_name)
+    base_model = AutoModelForCausalLM.from_pretrained(base_model_name)
+    
+    # Load the PEFT adapter
+    peft_model = PeftModel.from_pretrained(
+        base_model,
+        "ombhojane/smile-small",
+    )
+    
+    return pipeline(
+        "text-generation",
+        model=peft_model,
+        tokenizer=tokenizer,
+        device=device
+    )
+
+pipe = load_model()
 
 @spaces.GPU
 def generate_response(message):