Update app.py

app.py

@@ -9,7 +9,6 @@ import time
 import textwrap
 from PIL import Image
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from peft import PeftModel, PeftConfig
 import torch
 import os
 import uuid
@@ -354,7 +353,7 @@ class ChatBot:
     def doctor(user_input, system_prompt="You are an expert medical analyst:"): # TruEra
         formatted_input = f"{system_prompt}{user_input}"
         user_input_ids = tokenizer.encode(formatted_input, return_tensors="pt")
-        response = peft_model.generate(input_ids=user_input_ids, max_length=512, pad_token_id=tokenizer.eos_token_id)
+        response = model.generate(input_ids=user_input_ids, max_length=512, pad_token_id=tokenizer.eos_token_id)
         response_text = tokenizer.decode(response[0], skip_special_tokens=True)
         return response_text