Update app.py

app.py

@@ -1,13 +1,15 @@
 import re
 from peft import PeftModel, PeftConfig
-from transformers import AutoModelForCausalLM
-
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
 
 @spaces.GPU(duration=300)
-config = PeftConfig.from_pretrained("FlawedLLM/BhashiniLLM")
-base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-bnb-4bit")
-model = PeftModel.from_pretrained(base_model, "FlawedLLM/BhashiniLLM")
-tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/BhashiniLLM")
+
+model = AutoPeftModelForCausalLM.from_pretrained(
+    "FlawedLLM/BhashiniLLM", # YOUR MODEL YOU USED FOR TRAINING
+    load_in_4bit = load_in_4bit,
+)
+    tokenizer = AutoTokenizer.from_pretrained("lora_model")
 def chunk_it(input_command):
     inputs = tokenizer(
     [