Update app.py

app.py

@@ -18,13 +18,14 @@ def load_model(repo_name):
     model.to('cuda')
     return tokenizer, generator_conf, model
 
-tokenizer, generator_conf, model = load_model(REPO_NAME)
-
-global_error = ''
-try:
-    generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
-except Exception as e:
-    global_error =  f"Failed to load model: {str(e)}"
+tokenizer, generator_conf, model, generator = False, False, False, False 
+with gr.Blocks() as main_block:
+    tokenizer, generator_conf, model = load_model(REPO_NAME)
+    global_error = ''
+    try:
+        generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+    except Exception as e:
+        global_error =  f"Failed to load model: {str(e)}"
 
 @spaces.GPU()
 def respond(