Update app.py

app.py

@@ -1,9 +1,18 @@
 import gradio as gr
 from transformers import pipeline
 from typing import List, Tuple
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-# Initialize the model
-generator = pipeline("text-generation", model="BoghdadyJR/med")
+peft_model_id = "BoghdadyJR/med"
+config = PeftConfig.from_pretrained(peft_model_id)
+model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, device_map='auto')
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+# Load the Lora model
+model = PeftModel.from_pretrained(model, peft_model_id)
+
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 # Shortened system prompt
 system_prompt="""