def __init__(
self,
pretrained_model_name_or_path='ctrl',
reduce_output='sum',
trainable=True,
num_tokens=None,
**kwargs
):
super(CTRLEncoder, self).__init__()
try:
from transformers import TFCTRLModel
except ModuleNotFoundError:
logger.error(
' transformers is not installed. '
'In order to install all text feature dependencies run '
'pip install ludwig[text]'
)
sys.exit(-1)
self.transformer = TFCTRLModel.from_pretrained(
pretrained_model_name_or_path
)
self.reduce_output = reduce_output
self.reduce_sequence = SequenceReducer(reduce_mode=reduce_output)
self.transformer.trainable = trainable
self.transformer.resize_token_embeddings(num_tokens)
def test_TFCTRL(self):
from transformers import CTRLTokenizer, TFCTRLModel
tokenizer = CTRLTokenizer.from_pretrained('ctrl')
model = TFCTRLModel.from_pretrained('ctrl')
input_dict = tokenizer("Hello, my dog is cute", return_tensors="tf")
spec, input_dict = self.spec_and_pad(input_dict)
outputs = ["last_hidden_state"]
self.run_test(model, input_dict, input_signature=spec, outputs=outputs, large=True)