Spaces:
Paused
Paused
Update app.py
Browse files
app.py
CHANGED
|
@@ -93,9 +93,9 @@ if (should_train_model=='1'): #train model
|
|
| 93 |
|
| 94 |
repo_name = "Reyad-Ahmmed/hf-data-timeframe"
|
| 95 |
|
| 96 |
-
|
| 97 |
|
| 98 |
-
tokenizer = RobertaTokenizer.from_pretrained("roberta-base")
|
| 99 |
|
| 100 |
# I made sure to add all the ones in the training and eval data to this list
|
| 101 |
# since we are training using data that only contains the left tag - we don't need right tags added to this list
|
|
@@ -104,9 +104,9 @@ if (should_train_model=='1'): #train model
|
|
| 104 |
|
| 105 |
|
| 106 |
# Model
|
| 107 |
-
|
| 108 |
|
| 109 |
-
model = BertForSequenceClassification.from_pretrained("roberta-base", output_attentions=True, num_labels=len(label_mapping), output_hidden_states=True).to('cpu')
|
| 110 |
|
| 111 |
# Reset tokenizer size to include the new size after adding the tags to the tokenizer's tokens
|
| 112 |
model.resize_token_embeddings(len(tokenizer))
|
|
|
|
| 93 |
|
| 94 |
repo_name = "Reyad-Ahmmed/hf-data-timeframe"
|
| 95 |
|
| 96 |
+
tokenizer = BertTokenizer.from_pretrained(repo_name, subfolder="bert_embeddings_finetune")
|
| 97 |
|
| 98 |
+
#tokenizer = RobertaTokenizer.from_pretrained("roberta-base")
|
| 99 |
|
| 100 |
# I made sure to add all the ones in the training and eval data to this list
|
| 101 |
# since we are training using data that only contains the left tag - we don't need right tags added to this list
|
|
|
|
| 104 |
|
| 105 |
|
| 106 |
# Model
|
| 107 |
+
model = BertForSequenceClassification.from_pretrained(repo_name, subfolder="bert_embeddings_finetune", output_attentions=True, num_labels=len(label_mapping), output_hidden_states=True).to('cpu')
|
| 108 |
|
| 109 |
+
#model = BertForSequenceClassification.from_pretrained("roberta-base", output_attentions=True, num_labels=len(label_mapping), output_hidden_states=True).to('cpu')
|
| 110 |
|
| 111 |
# Reset tokenizer size to include the new size after adding the tags to the tokenizer's tokens
|
| 112 |
model.resize_token_embeddings(len(tokenizer))
|