Update app.py

app.py

@@ -8,6 +8,7 @@ from peft import PeftConfig, PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
+os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'expandable_segments:True'
 
 base_model_name = "google/gemma-7b"
 adapter_model_name = "samidh/cope-g7bq-2c-hs.s1.5fpc.9-sx.s1.5.9o-VL.s1.5.9-HR.s5-SH.s5-l5e5-e3-d25-r8"