Update app.py

app.py

@@ -4,12 +4,12 @@ from peft import AutoPeftModelForCausalLM
 from transformers import AutoTokenizer
 
 @spaces.GPU(duration=300)
-model = AutoPeftModelForCausalLM.from_pretrained(
+def chunk_it(input_command):
+    model = AutoPeftModelForCausalLM.from_pretrained(
     "FlawedLLM/BhashiniLLM", # YOUR MODEL YOU USED FOR TRAINING
     load_in_4bit = True,
-)
-tokenizer = AutoTokenizer.from_pretrained("lora_model")
-def chunk_it(input_command):
+    )
+    tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/BhashiniLLM")
     inputs = tokenizer(
     [
         alpaca_prompt.format(