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

Patch models (#6326)

Browse Source 
* TFAlbertFor{TokenClassification, MultipleChoice}

* Patch models

* BERT and TF BERT info


s

* Update check_repo
This commit is contained in:
Lysandre Debut
2020-08-10 10:39:17 -04:00
committed by GitHub
parent 6028ed92bd
commit b99098abc7
6 changed files with 37 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
src/transformers/modeling_bert.py
View File

@@ -933,7 +933,9 @@ class BertForPreTraining(BertPreTrainedModel):
class BertLMHeadModel(BertPreTrainedModel):
def __init__(self, config):
super().__init__(config)
assert config.is_decoder, "If you want to use `BertLMHeadModel` as a standalone, add `is_decoder=True`."
if not config.is_decoder:
logger.info("If you want to use `BertLMHeadModel` as a standalone, add `is_decoder=True.`")
self.bert = BertModel(config)
self.cls = BertOnlyMLMHead(config)
@@ -1036,9 +1038,12 @@ class BertLMHeadModel(BertPreTrainedModel):
class BertForMaskedLM(BertPreTrainedModel):
def __init__(self, config):
super().__init__(config)
assert (
not config.is_decoder
), "If you want to use `BertForMaskedLM` make sure `config.is_decoder=False` for bi-directional self-attention."
if config.is_decoder:
logger.info(
"If you want to use `TFBertForMaskedLM` make sure `config.is_decoder=False` for "
"bi-directional self-attention."
)
self.bert = BertModel(config)
self.cls = BertOnlyMLMHead(config)

13
src/transformers/modeling_tf_bert.py
View File

@@ -860,9 +860,12 @@ class TFBertForPreTraining(TFBertPreTrainedModel):
class TFBertForMaskedLM(TFBertPreTrainedModel, TFMaskedLanguageModelingLoss):
def __init__(self, config, *inputs, **kwargs):
super().__init__(config, *inputs, **kwargs)
assert (
not config.is_decoder
), "If you want to use `BertForMaskedLM` make sure `config.is_decoder=False` for bi-directional self-attention."
if config.is_decoder:
logger.info(
"If you want to use `TFBertForMaskedLM` make sure `config.is_decoder=False` for "
"bi-directional self-attention."
)
self.bert = TFBertMainLayer(config, name="bert")
self.mlm = TFBertMLMHead(config, self.bert.embeddings, name="mlm___cls")
@@ -936,7 +939,9 @@ class TFBertForMaskedLM(TFBertPreTrainedModel, TFMaskedLanguageModelingLoss):
class TFBertLMHeadModel(TFBertPreTrainedModel, TFCausalLanguageModelingLoss):
def __init__(self, config, *inputs, **kwargs):
super().__init__(config, *inputs, **kwargs)
assert config.is_decoder, "If you want to use `TFBertLMHeadModel` as a standalone, add `is_decoder=True.`"
if not config.is_decoder:
logger.info("If you want to use `TFBertLMHeadModel` as a standalone, add `is_decoder=True.`")
self.bert = TFBertMainLayer(config, name="bert")
self.mlm = TFBertMLMHead(config, self.bert.embeddings, name="mlm___cls")