Spaces:
Paused
Paused
Update app.py
Browse files
app.py
CHANGED
|
@@ -138,7 +138,7 @@ def train_function_no_sweeps(base_model_path): #, train_dataset, test_dataset)
|
|
| 138 |
#label2id = {v: k for k, v in id2label.items()}
|
| 139 |
|
| 140 |
|
| 141 |
-
base_model = AutoModelForTokenClassification.from_pretrained(base_model_path, num_labels=len(id2label), id2label=id2label, label2id=label2id)
|
| 142 |
|
| 143 |
'''
|
| 144 |
# Load the data from pickle files (replace with your local paths)
|
|
@@ -156,7 +156,7 @@ def train_function_no_sweeps(base_model_path): #, train_dataset, test_dataset)
|
|
| 156 |
'''
|
| 157 |
|
| 158 |
# Tokenization
|
| 159 |
-
tokenizer = AutoTokenizer.from_pretrained(base_model_path) #("facebook/esm2_t12_35M_UR50D")
|
| 160 |
#max_sequence_length = 1000
|
| 161 |
|
| 162 |
train_tokenized = tokenizer(train_sequences, padding=True, truncation=True, max_length=max_sequence_length, return_tensors="pt", is_split_into_words=False)
|
|
|
|
| 138 |
#label2id = {v: k for k, v in id2label.items()}
|
| 139 |
|
| 140 |
|
| 141 |
+
base_model = AutoModelForTokenClassification.from_pretrained(base_model_path, num_labels=len(id2label), id2label=id2label, label2id=label2id, token=HF_TOKEN)
|
| 142 |
|
| 143 |
'''
|
| 144 |
# Load the data from pickle files (replace with your local paths)
|
|
|
|
| 156 |
'''
|
| 157 |
|
| 158 |
# Tokenization
|
| 159 |
+
tokenizer = AutoTokenizer.from_pretrained(base_model_path, token=HF_TOKEN) #("facebook/esm2_t12_35M_UR50D")
|
| 160 |
#max_sequence_length = 1000
|
| 161 |
|
| 162 |
train_tokenized = tokenizer(train_sequences, padding=True, truncation=True, max_length=max_sequence_length, return_tensors="pt", is_split_into_words=False)
|