Update app.py

app.py

@@ -93,7 +93,10 @@ if (should_train_model=='1'): #train model
 
     repo_name = "Reyad-Ahmmed/hf-data-timeframe"
     
-    tokenizer = BertTokenizer.from_pretrained(repo_name, subfolder="bert_embeddings_finetune")
+    #tokenizer = BertTokenizer.from_pretrained(repo_name, subfolder="bert_embeddings_finetune
+    
+    tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
+                                              
     # I made sure to add all the ones in the training and eval data to this list
     # since we are training using data that only contains the left tag - we don't need right tags added to this list
     new_tokens = ['<EMPLOYEE_FIRST_NAME>', '<EMPLOYEE_LAST_NAME>','<POINT_ADDRESS>', '<TRUCK_NAME>', '<POINT_CLASS_NAME>', '<POINT_NAME>', '<TRUCK_CLASS_NAME>', '<TRUCK_STATUS_NAME>]']
@@ -101,7 +104,9 @@ if (should_train_model=='1'): #train model
 
     
     # Model
-    model = BertForSequenceClassification.from_pretrained(repo_name, subfolder="bert_embeddings_finetune", output_attentions=True, num_labels=len(label_mapping), output_hidden_states=True).to('cpu')
+    #model = BertForSequenceClassification.from_pretrained(repo_name, subfolder="bert_embeddings_finetune", output_attentions=True, num_labels=len(label_mapping), output_hidden_states=True).to('cpu')
+
+    model = BertForSequenceClassification.from_pretrained("bert-base-uncased", output_attentions=True, num_labels=len(label_mapping), output_hidden_states=True).to('cpu')
 
     # Reset tokenizer size to include the new size after adding the tags to the tokenizer's tokens
     model.resize_token_embeddings(len(tokenizer))