Skip to content

Rework automatic code samples in docstrings #20757

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sgugger merged 6 commits into from
Jan 14, 2023
Merged

Rework automatic code samples in docstrings #20757

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
85bd5f8
Rework automatic code samples in docstrings
sgugger Dec 13, 2022
5fa2c83
ImageProcessor->AutoImageProcessor
sgugger Dec 13, 2022
08d9fd3
Add models to fix copies
sgugger Dec 13, 2022
16b2c15
Last typos
sgugger Dec 13, 2022
42d6231
A couple more models
sgugger Dec 14, 2022
c0d1d4f
Fix copies
sgugger Jan 5, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 0 additions & 8 deletions src/transformers/models/bert/modeling_bert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,6 @@

_CHECKPOINT_FOR_DOC = "bert-base-uncased"
_CONFIG_FOR_DOC = "BertConfig"
_TOKENIZER_FOR_DOC = "BertTokenizer"

# TokenClassification docstring
_CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "dbmdz/bert-large-cased-finetuned-conll03-english"
Expand Down Expand Up @@ -911,7 +910,6 @@ class PreTrainedModel

@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=BaseModelOutputWithPoolingAndCrossAttentions,
config_class=_CONFIG_FOR_DOC,
Expand Down Expand Up @@ -1184,7 +1182,6 @@ def set_output_embeddings(self, new_embeddings):

@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
Copy link
Collaborator

@ydshieh ydshieh Dec 13, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

not sure why this is not added say as the last argument and same question below

Copy link
Collaborator Author

@sgugger sgugger Dec 13, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Because there is no processor_class in the code sample used by this model anymore. It's just in the base model, and I have just left it there in case it's used by other modalities.

output_type=CausalLMOutputWithCrossAttentions,
config_class=_CONFIG_FOR_DOC,
Expand Down Expand Up @@ -1327,7 +1324,6 @@ def set_output_embeddings(self, new_embeddings):

@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=MaskedLMOutput,
config_class=_CONFIG_FOR_DOC,
Expand Down Expand Up @@ -1535,7 +1531,6 @@ def __init__(self, config):

@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
output_type=SequenceClassifierOutput,
config_class=_CONFIG_FOR_DOC,
Expand Down Expand Up @@ -1637,7 +1632,6 @@ def __init__(self, config):

@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, num_choices, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=MultipleChoiceModelOutput,
config_class=_CONFIG_FOR_DOC,
Expand Down Expand Up @@ -1736,7 +1730,6 @@ def __init__(self, config):

@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION,
output_type=TokenClassifierOutput,
config_class=_CONFIG_FOR_DOC,
Expand Down Expand Up @@ -1819,7 +1812,6 @@ def __init__(self, config):

@add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_QA,
output_type=QuestionAnsweringModelOutput,
config_class=_CONFIG_FOR_DOC,
Expand Down
30 changes: 5 additions & 25 deletions src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,21 +51,8 @@

_CHECKPOINT_FOR_DOC = "google/bigbird-pegasus-large-arxiv"
_CONFIG_FOR_DOC = "BigBirdPegasusConfig"
_TOKENIZER_FOR_DOC = "PegasusTokenizerFast"

# Base model docstring
_EXPECTED_OUTPUT_SHAPE = [1, 7, 1024]

# SequenceClassification docstring
_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "hf-internal-testing/tiny-random-bigbird_pegasus"
_SEQ_CLASS_EXPECTED_LOSS = 0.69
_SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'"

# QuestionAsnwering docstring
_CHECKPOINT_FOR_QA = "hf-internal-testing/tiny-random-bigbird_pegasus"
_QA_EXPECTED_LOSS = 3.96
_QA_EXPECTED_OUTPUT = "''"


BIGBIRD_PEGASUS_PRETRAINED_MODEL_ARCHIVE_LIST = [
"google/bigbird-pegasus-large-arxiv",
Expand Down Expand Up @@ -2355,7 +2342,6 @@ def custom_forward(*inputs):
"The bare BigBirdPegasus Model outputting raw hidden-states without any specific head on top.",
BIGBIRD_PEGASUS_START_DOCSTRING,
)
# Copied from transformers.models.bart.modeling_bart.BartModel with Bart->BigBirdPegasus, BART->BIGBIRD_PEGASUS
class BigBirdPegasusModel(BigBirdPegasusPreTrainedModel):
_keys_to_ignore_on_load_missing = ["encoder.embed_tokens.weight", "decoder.embed_tokens.weight"]

Expand Down Expand Up @@ -2387,12 +2373,12 @@ def get_decoder(self):

@add_start_docstrings_to_model_forward(BIGBIRD_PEGASUS_INPUTS_DOCSTRING)
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=Seq2SeqModelOutput,
config_class=_CONFIG_FOR_DOC,
expected_output=_EXPECTED_OUTPUT_SHAPE,
)
# Copied from transformers.models.bart.modeling_bart.BartModel.forward with Bart->BigBirdPegasus
def forward(
self,
input_ids: torch.LongTensor = None,
Expand Down Expand Up @@ -2663,7 +2649,6 @@ def _reorder_cache(past, beam_idx):
""",
BIGBIRD_PEGASUS_START_DOCSTRING,
)
# Copied from transformers.models.bart.modeling_bart.BartForSequenceClassification with Bart->BigBirdPegasus, BART->BIGBIRD_PEGASUS
class BigBirdPegasusForSequenceClassification(BigBirdPegasusPreTrainedModel):
_keys_to_ignore_on_load_missing = ["encoder.embed_tokens.weight", "decoder.embed_tokens.weight"]

Expand All @@ -2681,13 +2666,11 @@ def __init__(self, config: BigBirdPegasusConfig, **kwargs):

@add_start_docstrings_to_model_forward(BIGBIRD_PEGASUS_INPUTS_DOCSTRING)
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=Seq2SeqSequenceClassifierOutput,
config_class=_CONFIG_FOR_DOC,
expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
)
# Copied from transformers.models.bart.modeling_bart.BartForSequenceClassification.forward
def forward(
self,
input_ids: torch.LongTensor = None,
Expand Down Expand Up @@ -2793,7 +2776,6 @@ def forward(
""",
BIGBIRD_PEGASUS_START_DOCSTRING,
)
# Copied from transformers.models.bart.modeling_bart.BartForQuestionAnswering with Bart->BigBirdPegasus, BART->BIGBIRD_PEGASUS
class BigBirdPegasusForQuestionAnswering(BigBirdPegasusPreTrainedModel):
_keys_to_ignore_on_load_missing = ["encoder.embed_tokens.weight", "decoder.embed_tokens.weight"]

Expand All @@ -2810,13 +2792,11 @@ def __init__(self, config):

@add_start_docstrings_to_model_forward(BIGBIRD_PEGASUS_INPUTS_DOCSTRING)
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_QA,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=Seq2SeqQuestionAnsweringModelOutput,
config_class=_CONFIG_FOR_DOC,
expected_loss=_QA_EXPECTED_LOSS,
expected_output=_QA_EXPECTED_OUTPUT,
)
# Copied from transformers.models.bart.modeling_bart.BartForQuestionAnswering.forward
def forward(
self,
input_ids: torch.Tensor = None,
Expand Down
39 changes: 8 additions & 31 deletions src/transformers/models/data2vec/modeling_data2vec_audio.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,6 @@

# General docstring
_CONFIG_FOR_DOC = "Data2VecAudioConfig"
_PROCESSOR_FOR_DOC = "Wav2Vec2Processor"

# Base docstring
_CHECKPOINT_FOR_DOC = "facebook/data2vec-audio-base-960h"
Expand All @@ -57,20 +56,6 @@
_CTC_EXPECTED_OUTPUT = "'MISTER QUILTER IS THE APOSTLE OF THE MIDDLE CLASSES AND WE ARE GLAD TO WELCOME HIS GOSPEL'"
_CTC_EXPECTED_LOSS = 66.95

# Audio class docstring
_FEAT_EXTRACTOR_FOR_DOC = "Wav2Vec2FeatureExtractor"
_SEQ_CLASS_CHECKPOINT = "hf-internal-testing/tiny-random-data2vec-seq-class"
_SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'"
_SEQ_CLASS_EXPECTED_LOSS = 0.69

# Frame class docstring
_FRAME_CLASS_CHECKPOINT = "hf-internal-testing/tiny-random-data2vec-audio-frame"
_FRAME_EXPECTED_OUTPUT = [1, 1]

# Speaker Verification docstring
_XVECTOR_CHECKPOINT = "hf-internal-testing/tiny-random-data2vec-xvector"
_XVECTOR_EXPECTED_OUTPUT = 1.0


DATA2VEC_AUDIO_PRETRAINED_MODEL_ARCHIVE_LIST = [
"facebook/data2vec-audio-base",
Expand Down Expand Up @@ -917,12 +902,12 @@ def _mask_hidden_states(

@add_start_docstrings_to_model_forward(DATA2VEC_AUDIO_INPUTS_DOCSTRING)
@add_code_sample_docstrings(
processor_class=_PROCESSOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=Wav2Vec2BaseModelOutput,
config_class=_CONFIG_FOR_DOC,
modality="audio",
expected_output=_EXPECTED_OUTPUT_SHAPE,
processor_class="AutoProcessor",
)
def forward(
self,
Expand Down Expand Up @@ -981,7 +966,6 @@ def forward(
"""Data2VecAudio Model with a `language modeling` head on top for Connectionist Temporal Classification (CTC).""",
DATA2VEC_AUDIO_START_DOCSTRING,
)
# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForCTC with Wav2Vec2->Data2VecAudio, wav2vec2->data2vec_audio, WAV_2_VEC_2->DATA2VEC_AUDIO
class Data2VecAudioForCTC(Data2VecAudioPreTrainedModel):
def __init__(self, config):
super().__init__(config)
Expand Down Expand Up @@ -1025,13 +1009,13 @@ def freeze_feature_encoder(self):

@add_start_docstrings_to_model_forward(DATA2VEC_AUDIO_INPUTS_DOCSTRING)
@add_code_sample_docstrings(
processor_class=_PROCESSOR_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=CausalLMOutput,
config_class=_CONFIG_FOR_DOC,
expected_output=_CTC_EXPECTED_OUTPUT,
expected_loss=_CTC_EXPECTED_LOSS,
)
# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForCTC.forward with wav2vec2->data2vec_audio
def forward(
self,
input_values: Optional[torch.Tensor],
Expand Down Expand Up @@ -1112,7 +1096,6 @@ def forward(
""",
DATA2VEC_AUDIO_START_DOCSTRING,
)
# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForSequenceClassification with Wav2Vec2->Data2VecAudio, wav2vec2->data2vec_audio, WAV_2_VEC_2->DATA2VEC_AUDIO
class Data2VecAudioForSequenceClassification(Data2VecAudioPreTrainedModel):
def __init__(self, config):
super().__init__(config)
Expand Down Expand Up @@ -1160,14 +1143,12 @@ def freeze_base_model(self):

@add_start_docstrings_to_model_forward(DATA2VEC_AUDIO_INPUTS_DOCSTRING)
@add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_SEQ_CLASS_CHECKPOINT,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=SequenceClassifierOutput,
config_class=_CONFIG_FOR_DOC,
modality="audio",
expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
)
# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForSequenceClassification.forward with wav2vec2->data2vec_audio
def forward(
self,
input_values: Optional[torch.Tensor],
Expand Down Expand Up @@ -1236,7 +1217,6 @@ def forward(
""",
DATA2VEC_AUDIO_START_DOCSTRING,
)
# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForAudioFrameClassification with Wav2Vec2->Data2VecAudio, wav2vec2->data2vec_audio, WAV_2_VEC_2->DATA2VEC_AUDIO
class Data2VecAudioForAudioFrameClassification(Data2VecAudioPreTrainedModel):
def __init__(self, config):
super().__init__(config)
Expand Down Expand Up @@ -1284,13 +1264,12 @@ def freeze_base_model(self):

@add_start_docstrings_to_model_forward(DATA2VEC_AUDIO_INPUTS_DOCSTRING)
@add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_FRAME_CLASS_CHECKPOINT,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TokenClassifierOutput,
config_class=_CONFIG_FOR_DOC,
modality="audio",
expected_output=_FRAME_EXPECTED_OUTPUT,
)
# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForAudioFrameClassification.forward with wav2vec2->data2vec_audio
def forward(
self,
input_values: Optional[torch.Tensor],
Expand Down Expand Up @@ -1402,7 +1381,6 @@ def forward(self, hidden_states):
""",
DATA2VEC_AUDIO_START_DOCSTRING,
)
# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForXVector with Wav2Vec2->Data2VecAudio, wav2vec2->data2vec_audio, WAV_2_VEC_2->DATA2VEC_AUDIO
class Data2VecAudioForXVector(Data2VecAudioPreTrainedModel):
def __init__(self, config):
super().__init__(config)
Expand Down Expand Up @@ -1467,13 +1445,12 @@ def _conv_out_length(input_length, kernel_size, stride):

@add_start_docstrings_to_model_forward(DATA2VEC_AUDIO_INPUTS_DOCSTRING)
@add_code_sample_docstrings(
processor_class=_FEAT_EXTRACTOR_FOR_DOC,
checkpoint=_XVECTOR_CHECKPOINT,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=XVectorOutput,
config_class=_CONFIG_FOR_DOC,
modality="audio",
expected_output=_XVECTOR_EXPECTED_OUTPUT,
)
# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForXVector.forward with wav2vec2->data2vec_audio
def forward(
self,
input_values: Optional[torch.Tensor],
Expand Down
27 changes: 2 additions & 25 deletions src/transformers/models/deberta/modeling_deberta.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,34 +38,20 @@

logger = logging.get_logger(__name__)
_CONFIG_FOR_DOC = "DebertaConfig"
_TOKENIZER_FOR_DOC = "DebertaTokenizer"
_CHECKPOINT_FOR_DOC = "microsoft/deberta-base"

# Masked LM docstring
_CHECKPOINT_FOR_MASKED_LM = "lsanochkin/deberta-large-feedback"
_MASKED_LM_EXPECTED_OUTPUT = "' Paris'"
_MASKED_LM_EXPECTED_LOSS = "0.54"

# TokenClassification docstring
_CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "dbsamu/deberta-base-finetuned-ner"
_TOKEN_CLASS_EXPECTED_OUTPUT = (
"['LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0',"
" 'LABEL_0', 'LABEL_0']"
)
_TOKEN_CLASS_EXPECTED_LOSS = 0.04

# QuestionAnswering docstring
_CHECKPOINT_FOR_QA = "Palak/microsoft_deberta-large_squad"
_QA_EXPECTED_OUTPUT = "' a nice puppet'"
_QA_EXPECTED_LOSS = 0.14
_QA_TARGET_START_INDEX = 12
_QA_TARGET_END_INDEX = 14

# SequenceClassification docstring
_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "hf-internal-testing/tiny-random-deberta"
_SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_0'"
_SEQ_CLASS_EXPECTED_LOSS = "0.69"


DEBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = [
"microsoft/deberta-base",
Expand Down Expand Up @@ -950,7 +936,6 @@ class PreTrainedModel

@add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=BaseModelOutput,
config_class=_CONFIG_FOR_DOC,
Expand Down Expand Up @@ -1057,7 +1042,6 @@ def set_output_embeddings(self, new_embeddings):

@add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_MASKED_LM,
output_type=MaskedLMOutput,
config_class=_CONFIG_FOR_DOC,
Expand Down Expand Up @@ -1201,12 +1185,9 @@ def set_input_embeddings(self, new_embeddings):

@add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=SequenceClassifierOutput,
config_class=_CONFIG_FOR_DOC,
expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
)
def forward(
self,
Expand Down Expand Up @@ -1311,12 +1292,9 @@ def __init__(self, config):

@add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION,
checkpoint=_CHECKPOINT_FOR_DOC,
output_type=TokenClassifierOutput,
config_class=_CONFIG_FOR_DOC,
expected_output=_TOKEN_CLASS_EXPECTED_OUTPUT,
expected_loss=_TOKEN_CLASS_EXPECTED_LOSS,
)
def forward(
self,
Expand Down Expand Up @@ -1388,7 +1366,6 @@ def __init__(self, config):

@add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
@add_code_sample_docstrings(
processor_class=_TOKENIZER_FOR_DOC,
checkpoint=_CHECKPOINT_FOR_QA,
output_type=QuestionAnsweringModelOutput,
config_class=_CONFIG_FOR_DOC,
Expand Down
Loading