Update app.py

app.py

@@ -5,11 +5,11 @@ from transformers import AutoProcessor, Llama4ForConditionalGeneration
 
 import torch
 
-# from transformers import BitsAndBytesConfig
-# bnb_config = BitsAndBytesConfig(
-#     load_in_4bit=True,
-#     llm_int8_enable_fp32_cpu_offload=True,
-# )
+from transformers import BitsAndBytesConfig
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    llm_int8_enable_fp32_cpu_offload=True,
+)
 
 #Qwen/Qwen2.5-14B-Instruct-1M
 #Qwen/Qwen2-0.5B