Update app.py

app.py

@@ -1,19 +1,17 @@
 import os
 os.system("pip install -q gradio torch")
-os.system('pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"')
 os.system('pip install --no-deps xformers "trl<0.9.0" peft accelerate bitsandbytes')
 
 import gradio as gr
 import torch
 import random
-from unsloth import FastLanguageModel
-from peft import PeftModel
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
 max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
 dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
 load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
 
-model, tokenizer = FastLanguageModel.from_pretrained(
+model, tokenizer = AutoModelForCausalLM.from_pretrained(
     model_name = "Qwen/Qwen2-1.5B",
     max_seq_length = max_seq_length,
     dtype = dtype,