Update app.py

app.py

@@ -1,15 +1,5 @@
 import streamlit as st
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from peft import get_peft_model, LoraConfig
-
-# Define the same LoRA configuration used during fine-tuning
-lora_config = LoraConfig(
-    r=8,  # Low-rank parameter
-    lora_alpha=32,  # Scaling parameter
-    lora_dropout=0.1,  # Dropout rate
-    target_modules=["q", "v"],  # The attention layers to apply LoRA to
-    bias="none"
-)
 
 # Load the model and tokenizer from Hugging Face's hub
 tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")