SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fix template for inputs docstrings (#12976)

Browse Source
This commit is contained in:
Sylvain Gugger
2021-08-03 08:28:25 +02:00
committed by GitHub
parent 75b8990d90
commit 790f1c9545
15 changed files with 76 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py
View File

@@ -696,7 +696,7 @@ class {{cookiecutter.camelcase_modelname}}PreTrainedModel(PreTrainedModel):
{{cookiecutter.uppercase_modelname}}_INPUTS_DOCSTRING = r"""
Args:
input_ids (:obj:`torch.LongTensor` of shape :obj:`{0}`):
input_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`):
Indices of input sequence tokens in the vocabulary.
Indices can be obtained using :class:`transformers.{{cookiecutter.camelcase_modelname}}Tokenizer`.
@@ -704,14 +704,14 @@ class {{cookiecutter.camelcase_modelname}}PreTrainedModel(PreTrainedModel):
:func:`transformers.PreTrainedTokenizer.__call__` for details.
`What are input IDs? <../glossary.html#input-ids>`__
attention_mask (:obj:`torch.FloatTensor` of shape :obj:`{0}`, `optional`):
attention_mask (:obj:`torch.FloatTensor` of shape :obj:`({0})`, `optional`):
Mask to avoid performing attention on padding token indices. Mask values selected in ``[0, 1]``:
- 1 for tokens that are **not masked**,
- 0 for tokens that are **masked**.
`What are attention masks? <../glossary.html#attention-mask>`__
token_type_ids (:obj:`torch.LongTensor` of shape :obj:`{0}`, `optional`):
token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
Segment token indices to indicate first and second portions of the inputs. Indices are selected in ``[0,
1]``:
@@ -719,7 +719,7 @@ class {{cookiecutter.camelcase_modelname}}PreTrainedModel(PreTrainedModel):
- 1 corresponds to a `sentence B` token.
`What are token type IDs? <../glossary.html#token-type-ids>`_
position_ids (:obj:`torch.LongTensor` of shape :obj:`{0}`, `optional`):
position_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
Indices of positions of each input sequence tokens in the position embeddings.
Selected in the range ``[0, config.max_position_embeddings - 1]``.
@@ -730,7 +730,7 @@ class {{cookiecutter.camelcase_modelname}}PreTrainedModel(PreTrainedModel):
- 1 indicates the head is **not masked**,
- 0 indicates the head is **masked**.
inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`({0}, hidden_size)`, `optional`):
Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
This is useful if you want more control over how to convert `input_ids` indices into associated vectors
than the model's internal embedding lookup matrix.
@@ -788,7 +788,7 @@ class {{cookiecutter.camelcase_modelname}}Model({{cookiecutter.camelcase_modelna
for layer, heads in heads_to_prune.items():
self.encoder.layer[layer].attention.prune_heads(heads)
@add_start_docstrings_to_model_forward({{cookiecutter.uppercase_modelname}}_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
@add_start_docstrings_to_model_forward({{cookiecutter.uppercase_modelname}}_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
@@ -947,7 +947,7 @@ class {{cookiecutter.camelcase_modelname}}ForMaskedLM({{cookiecutter.camelcase_m
def set_output_embeddings(self, new_embeddings):
self.cls.predictions.decoder = new_embeddings
@add_start_docstrings_to_model_forward({{cookiecutter.uppercase_modelname}}_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
@add_start_docstrings_to_model_forward({{cookiecutter.uppercase_modelname}}_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
@@ -1385,7 +1385,7 @@ class {{cookiecutter.camelcase_modelname}}ForTokenClassification({{cookiecutter.
self.init_weights()
@add_start_docstrings_to_model_forward({{cookiecutter.uppercase_modelname}}_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
@add_start_docstrings_to_model_forward({{cookiecutter.uppercase_modelname}}_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
@@ -1472,7 +1472,7 @@ class {{cookiecutter.camelcase_modelname}}ForQuestionAnswering({{cookiecutter.ca
self.init_weights()
@add_start_docstrings_to_model_forward({{cookiecutter.uppercase_modelname}}_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
@add_start_docstrings_to_model_forward({{cookiecutter.uppercase_modelname}}_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
tokenizer_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,