def prepare_config_and_inputs(self):
input_ids = ids_tensor([self.batch_size, self.seq_length], self.vocab_size)
input_mask = None
if self.use_input_mask:
input_mask = ids_tensor([self.batch_size, self.seq_length], vocab_size=2)
token_type_ids = None
if self.use_token_type_ids:
token_type_ids = ids_tensor([self.batch_size, self.seq_length], self.type_vocab_size)
sequence_labels = None
token_labels = None
choice_labels = None
if self.use_labels:
sequence_labels = ids_tensor([self.batch_size], self.type_sequence_label_size)
token_labels = ids_tensor([self.batch_size, self.seq_length], self.num_labels)
choice_labels = ids_tensor([self.batch_size], self.num_choices)
config = ConvBertConfig(
vocab_size=self.vocab_size,
hidden_size=self.hidden_size,
num_hidden_layers=self.num_hidden_layers,
num_attention_heads=self.num_attention_heads,
intermediate_size=self.intermediate_size,
hidden_act=self.hidden_act,
hidden_dropout_prob=self.hidden_dropout_prob,
attention_probs_dropout_prob=self.attention_probs_dropout_prob,
max_position_embeddings=self.max_position_embeddings,
type_vocab_size=self.type_vocab_size,
initializer_range=self.initializer_range,
return_dict=True,
)
return config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
def load_config(self):
config = ConvBertConfig(
label2id=self.params.tag2id,
id2label=self.params.id2tag,
max_position_embeddings=1580).from_pretrained(
"sarnikowski/convbert-medium-small-da-cased",
finetuning_task="ner")
return config
def convert_orig_tf1_checkpoint_to_pytorch(tf_checkpoint_path,
convbert_config_file,
pytorch_dump_path):
conf = ConvBertConfig.from_json_file(convbert_config_file)
model = ConvBertModel(conf)
model = load_tf_weights_in_convbert(model, conf, tf_checkpoint_path)
model.save_pretrained(pytorch_dump_path)
def load_context(self, context):
""" function to enable loading flow mlflow """
self.tokenizer = ConvBertTokenizerFast.from_pretrained(
context.artifacts["tokenizer_dir"],
config=ConvBertConfig.from_pretrained(
os.path.join(context.artifacts["tokenizer_dir"],
"tokenizer_config.json")),
)
self.model = ConvBertForSequenceClassification.from_pretrained(
context.artifacts["model_dir"], return_dict=True)
self.model.eval() # Put model in evaluation mode.
def get_config(self):
return ConvBertConfig(
vocab_size=self.vocab_size,
hidden_size=self.hidden_size,
num_hidden_layers=self.num_hidden_layers,
num_attention_heads=self.num_attention_heads,
intermediate_size=self.intermediate_size,
hidden_act=self.hidden_act,
hidden_dropout_prob=self.hidden_dropout_prob,
attention_probs_dropout_prob=self.attention_probs_dropout_prob,
max_position_embeddings=self.max_position_embeddings,
type_vocab_size=self.type_vocab_size,
is_decoder=False,
initializer_range=self.initializer_range,
)