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

Refactor Code samples; Test code samples (#5036)

Browse Source 
* Refactor code samples

* Test docstrings

* Style

* Tokenization examples

* Run rust of tests

* First step to testing source docs

* Style and BART comment

* Test the remainder of the code samples

* Style

* let to const

* Formatting fixes

* Ready for merge

* Fix fixture + Style

* Fix last tests

* Update docs/source/quicktour.rst

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Addressing @sgugger's comments + Fix MobileBERT in TF

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
This commit is contained in:
Lysandre Debut
2020-06-25 16:46:00 -04:00
committed by GitHub
parent 315f464b0a
commit 364a5ae1f0
68 changed files with 1962 additions and 2979 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
src/transformers/modeling_ctrl.py
View File

@@ -24,12 +24,14 @@ import torch.nn as nn
from torch.nn import CrossEntropyLoss
from .configuration_ctrl import CTRLConfig
from .file_utils import add_start_docstrings, add_start_docstrings_to_callable
from .file_utils import add_code_sample_docstrings, add_start_docstrings, add_start_docstrings_to_callable
from .modeling_utils import Conv1D, PreTrainedModel, find_pruneable_heads_and_indices, prune_linear_layer
logger = logging.getLogger(__name__)
_TOKENIZER_FOR_DOC = "CTRLTokenizer"
CTRL_PRETRAINED_MODEL_ARCHIVE_LIST = [
"ctrl"
# See all CTRL models at https://huggingface.co/models?filter=ctrl
@@ -326,6 +328,7 @@ class CTRLModel(CTRLPreTrainedModel):
self.h[layer].multi_head_attention.prune_heads(heads)
@add_start_docstrings_to_callable(CTRL_INPUTS_DOCSTRING)
@add_code_sample_docstrings(tokenizer_class=_TOKENIZER_FOR_DOC, checkpoint="ctrl")
def forward(
self,
input_ids=None,
@@ -358,20 +361,6 @@ class CTRLModel(CTRLPreTrainedModel):
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
Examples::
from transformers import CTRLTokenizer, CTRLModel
import torch
tokenizer = CTRLTokenizer.from_pretrained('ctrl')
model = CTRLModel.from_pretrained('ctrl')
input_ids = torch.tensor(tokenizer.encode("Links Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0) # Batch size 1
outputs = model(input_ids)
last_hidden_states = outputs[0] # The last hidden-state is the first element of the output tuple
"""
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
use_cache = use_cache if use_cache is not None else self.config.use_cache
@@ -510,6 +499,7 @@ class CTRLLMHeadModel(CTRLPreTrainedModel):
return {"input_ids": input_ids, "past": past, "use_cache": kwargs["use_cache"]}
@add_start_docstrings_to_callable(CTRL_INPUTS_DOCSTRING)
@add_code_sample_docstrings(tokenizer_class=_TOKENIZER_FOR_DOC, checkpoint="ctrl")
def forward(
self,
input_ids=None,
@@ -552,19 +542,6 @@ class CTRLLMHeadModel(CTRLPreTrainedModel):
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
Examples::
import torch
from transformers import CTRLTokenizer, CTRLLMHeadModel
tokenizer = CTRLTokenizer.from_pretrained('ctrl')
model = CTRLLMHeadModel.from_pretrained('ctrl')
input_ids = torch.tensor(tokenizer.encode("Links Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=input_ids)
loss, logits = outputs[:2]
"""
transformer_outputs = self.transformer(
input_ids,