Update app.py

app.py

@@ -65,8 +65,8 @@ def check_by_url(txt_url):
     new_data = {"title": title, "content": normalized_content_with_style}
 #     return new_data
 
-    model = DistilBertForSequenceClassification.from_pretrained("/content/LoadModel")
-    tokenizer = DistilBertTokenizer.from_pretrained("/content/LoadModel")
+    model = DistilBertForSequenceClassification.from_pretrained(".")
+    tokenizer = DistilBertTokenizer.from_pretrained(".")
 
     label_mapping = {1: "SFW", 0: "NSFW"} 
     test_encodings = tokenizer.encode_plus(
@@ -137,8 +137,8 @@ def predict_2(txt_url, normalized_content_with_style):
             new_data,
       ) = check_by_url(txt_url)
   elif txt_url.startswith(""):
-    model = DistilBertForSequenceClassification.from_pretrained("/content/LoadModel")
-    tokenizer = DistilBertTokenizer.from_pretrained("/content/LoadModel")
+    model = DistilBertForSequenceClassification.from_pretrained(".")
+    tokenizer = DistilBertTokenizer.from_pretrained(".")
 
     test_encodings = tokenizer.encode_plus(
             normalized_content_with_style,
@@ -185,8 +185,8 @@ def word_by_word(txt_url, normalized_content_with_style):
             confidence_score_text,
       ) = predict_2(txt_url, normalized_content_with_style)
 
-  model = DistilBertForSequenceClassification.from_pretrained("/content/LoadModel")
-  tokenizer = DistilBertTokenizer.from_pretrained("/content/LoadModel")      
+  model = DistilBertForSequenceClassification.from_pretrained(".")
+  tokenizer = DistilBertTokenizer.from_pretrained(".")      
   device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
   model = model.to(device)
   model.eval()