Update app_v3.py

app_v3.py

@@ -3,7 +3,7 @@ from transformers import AutoTokenizer, TextStreamer, pipeline
 from auto_gptq import AutoGPTQForCausalLM
 from huggingface_hub import snapshot_download
 import os
-#import gc
+import torch
 
 os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'max_split_size_mb:128'
 os.environ['CUDA_VISIBLE_DEVICES'] = '0'  # Assuming you want to use GPU 0