Update app.py

app.py

@@ -21,6 +21,9 @@ MODEL = None
 PROCESSOR = None
 DEVICE = None
 
+os.environ['TOKENIZERS_PARALLELISM'] = 'false'
+os.environ['TRANSFORMERS_CACHE'] = '/tmp/transformers_cache'
+
 def get_device():
     """Determine the best available device"""
     if torch.cuda.is_available():
@@ -28,7 +31,7 @@ def get_device():
     else:
         return "cpu"
 
-def load_model_cached(model_name: str = "Qwen/Qwen2.5-VL-3B-Instruct"):
+def load_model_cached(model_name: str = "Qwen/Qwen2-VL-2B-Instruct"):
     """Load and cache model - optimized for HF Spaces"""
     global MODEL, PROCESSOR, DEVICE