Update app.py

app.py

@@ -238,28 +238,15 @@ else:
 
     #model_save_path = "./" + modelNameToUse + "_model"
     #tokenizer_save_path = "./" + modelNameToUse + "_tokenizer"
-    
-    model_save_path = "./data-timeframe_model"
-    tokenizer_save_path = "./data-timeframe_tokenizer"
-    
-    # Check for specific files in the model directory
-    model_files = os.listdir(model_save_path)
-    model_files = [file for file in model_files]
-    print("Specific files in model directory:", model_files)
-    
-    # Check for specific files in the tokenizer directory
-    tokenizer_files = os.listdir(tokenizer_save_path)
-    tokenizer_files = [file for file in tokenizer_files]
-    print("Specific files in tokenizer directory:", tokenizer_files)
-    
-    #model_name = "Reyad-Ahmmed/hf-data-timeframe"
+
+    model_name = "Reyad-Ahmmed/hf-data-timeframe"
 
     # RobertaTokenizer.from_pretrained(model_save_path)
-    #model = AutoModelForSequenceClassification.from_pretrained(model_name, subfolder="data-timeframe_model").to('cpu')
-    #tokenizer = AutoTokenizer.from_pretrained(model_name, subfolder="data-timeframe_tokenizer")
+    model = AutoModelForSequenceClassification.from_pretrained(model_name, subfolder="data-timeframe_model").to('cpu')
+    tokenizer = AutoTokenizer.from_pretrained(model_name, subfolder="data-timeframe_tokenizer")
 
-    model = AutoModelForSequenceClassification.from_pretrained(model_save_path).to('cpu')
-    tokenizer = AutoTokenizer.from_pretrained(tokenizer_save_path)
+    #model = AutoModelForSequenceClassification.from_pretrained(model_save_path).to('cpu')
+    #tokenizer = AutoTokenizer.from_pretrained(tokenizer_save_path)
 
 #Define the label mappings (this must match the mapping used during training)
 label_mapping = {