def setup_jiant_model(
hf_pretrained_model_name_or_path: str,
model_config_path: str,
task_dict: Dict[str, Task],
taskmodels_config: container_setup.TaskmodelsConfig,
):
"""Sets up tokenizer, encoder, and task models, and instantiates and returns a JiantModel.
Args:
hf_pretrained_model_name_or_path (:obj:`str` or :obj:`os.PathLike`):
Can be either:
- A string, the `model id` of a predefined tokenizer hosted inside a model
repo on huggingface.co. Valid model ids can be located at the root-level,
like ``bert-base-uncased``, or namespaced under
a user or organization name, like ``dbmdz/bert-base-german-cased``.
- A path to a `directory` containing vocabulary files required by the
tokenizer, for instance saved using the
:func:`~transformers.PreTrainedTokenizer.save_pretrained` method, e.g.,
``./my_model_directory/``.
- A path or url to a single saved vocabulary file if and only if
the tokenizer only requires a single vocabulary file (like Bert or XLNet),
e.g.: ``./my_model_directory/vocab.txt``. (Not
applicable to all derived classes)
model_config_path (str): Path to the JSON file containing the configuration parameters.
task_dict (Dict[str, tasks.Task]): map from task name to task instance.
taskmodels_config: maps mapping from tasks to models, and specifying task-model configs.
Returns:
JiantModel nn.Module.
"""
if hf_pretrained_model_name_or_path == "roberta-base":
encoder = mixer_l16_224() #mixer_s16_224()
# hf_model = transformers.AutoModel.from_pretrained(hf_pretrained_model_name_or_path)
# print("hf_model: ", hf_model)
# exit(0)
tokenizer = transformers.AutoTokenizer.from_pretrained(
hf_pretrained_model_name_or_path, use_fast=False
)
print("tokenizer", tokenizer)
# exit(0)
# encoder = primary.JiantTransformersModelFactory()(hf_model)
taskmodels_dict = {
taskmodel_name: create_taskmodel(
task=task_dict[task_name_list[0]], # Take the first task
encoder=encoder,
taskmodel_kwargs=taskmodels_config.get_taskmodel_kwargs(taskmodel_name),
)
for taskmodel_name, task_name_list in get_taskmodel_and_task_names(
taskmodels_config.task_to_taskmodel_map
).items()
}
return primary.JiantModel(
task_dict=task_dict,
encoder=encoder,
taskmodels_dict=taskmodels_dict,
task_to_taskmodel_map=taskmodels_config.task_to_taskmodel_map,
tokenizer=tokenizer,
)
def setup_jiant_model(
model_type: str,
model_config_path: str,
tokenizer_path: str,
task_dict: Dict[str, Task],
taskmodels_config: container_setup.TaskmodelsConfig,
):
"""Sets up tokenizer, encoder, and task models, and instantiates and returns a JiantModel.
Args:
model_type (str): model shortcut name.
model_config_path (str): Path to the JSON file containing the configuration parameters.
tokenizer_path (str): path to tokenizer directory.
task_dict (Dict[str, tasks.Task]): map from task name to task instance.
taskmodels_config: maps mapping from tasks to models, and specifying task-model configs.
Returns:
JiantModel nn.Module.
"""
model_arch = ModelArchitectures.from_model_type(model_type)
transformers_class_spec = TRANSFORMERS_CLASS_SPEC_DICT[model_arch]
tokenizer = model_setup.get_tokenizer(model_type=model_type,
tokenizer_path=tokenizer_path)
ancestor_model = get_ancestor_model(
transformers_class_spec=transformers_class_spec,
model_config_path=model_config_path,
)
encoder = get_encoder(model_arch=model_arch, ancestor_model=ancestor_model)
taskmodels_dict = {
taskmodel_name: create_taskmodel(
task=task_dict[task_name_list[0]], # Take the first task
model_arch=model_arch,
encoder=encoder,
taskmodel_kwargs=taskmodels_config.get_taskmodel_kwargs(
taskmodel_name),
)
for taskmodel_name, task_name_list in get_taskmodel_and_task_names(
taskmodels_config.task_to_taskmodel_map).items()
}
return primary.JiantModel(
task_dict=task_dict,
encoder=encoder,
taskmodels_dict=taskmodels_dict,
task_to_taskmodel_map=taskmodels_config.task_to_taskmodel_map,
tokenizer=tokenizer,
)
def setup_jiant_model(
hf_pretrained_model_name_or_path: str,
model_config_path: str,
task_dict: Dict[str, Task],
taskmodels_config: container_setup.TaskmodelsConfig,
):
"""Sets up tokenizer, encoder, and task models, and instantiates and returns a JiantModel.
Args:
hf_pretrained_model_name_or_path (:obj:`str` or :obj:`os.PathLike`):
Can be either:
- A string, the `model id` of a predefined tokenizer hosted inside a model
repo on huggingface.co. Valid model ids can be located at the root-level,
like ``bert-base-uncased``, or namespaced under
a user or organization name, like ``dbmdz/bert-base-german-cased``.
- A path to a `directory` containing vocabulary files required by the
tokenizer, for instance saved using the
:func:`~transformers.PreTrainedTokenizer.save_pretrained` method, e.g.,
``./my_model_directory/``.
- A path or url to a single saved vocabulary file if and only if
the tokenizer only requires a single vocabulary file (like Bert or XLNet),
e.g.: ``./my_model_directory/vocab.txt``. (Not
applicable to all derived classes)
model_config_path (str): Path to the JSON file containing the configuration parameters.
task_dict (Dict[str, tasks.Task]): map from task name to task instance.
taskmodels_config: maps mapping from tasks to models, and specifying task-model configs.
Returns:
JiantModel nn.Module.
"""
model = transformers.AutoModel.from_pretrained(
hf_pretrained_model_name_or_path)
model_arch = ModelArchitectures.from_model_type(model.base_model_prefix)
transformers_class_spec = TRANSFORMERS_CLASS_SPEC_DICT[model_arch]
tokenizer = transformers.AutoTokenizer.from_pretrained(
hf_pretrained_model_name_or_path)
if (os.path.isdir(hf_pretrained_model_name_or_path)):
model_config_path = hf_pretrained_model_name_or_path + "/config.json"
ancestor_model = get_ancestor_model(
transformers_class_spec=transformers_class_spec,
model_config_path=model_config_path,
)
encoder = get_encoder(model_arch=model_arch, ancestor_model=ancestor_model)
taskmodels_dict = {
taskmodel_name: create_taskmodel(
task=task_dict[task_name_list[0]], # Take the first task
model_arch=model_arch,
encoder=encoder,
taskmodel_kwargs=taskmodels_config.get_taskmodel_kwargs(
taskmodel_name),
)
for taskmodel_name, task_name_list in get_taskmodel_and_task_names(
taskmodels_config.task_to_taskmodel_map).items()
}
return primary.JiantModel(
task_dict=task_dict,
encoder=encoder,
taskmodels_dict=taskmodels_dict,
task_to_taskmodel_map=taskmodels_config.task_to_taskmodel_map,
tokenizer=tokenizer,
)