Update app.py

app.py

@@ -3,8 +3,17 @@ from transformers import pipeline
 
 model_id = "thrishala/mental_health_chatbot"
 
+model_id = "thrishala/mental_health_chatbot"
+
 try:
-    pipe = pipeline("text-generation", model=model_id)  # Directly create pipeline
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(
+        model_id,
+        load_in_8bit=True,  # Load in 8-bit quantization
+        device_map="auto", #Use GPU if available
+        torch_dtype=torch.float16 #Use float 16 for additional memory reduction
+    )
+    pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 except Exception as e:
     print(f"Error loading model: {e}")