pretraining/fairseq/models/hf_bert.py [391:598]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - class PreTrainedBertModel(nn.Module): """ An abstract class to handle weights initialization and a simple interface for dowloading and loading pretrained models. """ def __init__(self, config, *inputs, **kwargs): super(PreTrainedBertModel, self).__init__() if not isinstance(config, BertConfig): raise ValueError( "Parameter config in `{}(config)` should be an instance of class `BertConfig`. " "To create a model from a Google pretrained model use " "`model = {}.from_pretrained(PRETRAINED_MODEL_NAME)`".format( self.__class__.__name__, self.__class__.__name__ )) self.config = config def init_bert_weights(self, module): """ Initialize the weights. """ if isinstance(module, (nn.Linear, nn.Embedding)): # Slightly different from the TF version which uses truncated_normal for initialization # cf https://github.com/pytorch/pytorch/pull/5617 module.weight.data.normal_(mean=0.0, std=self.config.initializer_range) elif isinstance(module, BertLayerNorm): module.beta.data.zero_() module.gamma.data.fill_(1.0) if isinstance(module, nn.Linear) and module.bias is not None: module.bias.data.zero_() @classmethod def from_pretrained(cls, pretrained_model_name, state_dict=None, cache_dir=None, *inputs, **kwargs): """ Instantiate a PreTrainedBertModel from a pre-trained model file or a pytorch state dict. Download and cache the pre-trained model file if needed. Params: pretrained_model_name: either: - a str with the name of a pre-trained model to load selected in the list of: . `bert-base-uncased` . `bert-large-uncased` . `bert-base-cased` . `bert-large-cased` . `bert-base-multilingual-uncased` . `bert-base-multilingual-cased` . `bert-base-chinese` - a path or url to a pretrained model archive containing: . `bert_config.json` a configuration file for the model . `pytorch_model.bin` a PyTorch dump of a BertForPreTraining instance cache_dir: an optional path to a folder in which the pre-trained models will be cached. state_dict: an optional state dictionnary (collections.OrderedDict object) to use instead of Google pre-trained models *inputs, **kwargs: additional input for the specific Bert class (ex: num_labels for BertForSequenceClassification) """ if pretrained_model_name in PRETRAINED_MODEL_ARCHIVE_MAP: archive_file = PRETRAINED_MODEL_ARCHIVE_MAP[pretrained_model_name] else: archive_file = pretrained_model_name # redirect to the cache, if necessary try: resolved_archive_file = cached_path(archive_file, cache_dir=cache_dir) except FileNotFoundError: logger.error( "Model name '{}' was not found in model name list ({}). " "We assumed '{}' was a path or url but couldn't find any file " "associated to this path or url.".format( pretrained_model_name, ', '.join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()), archive_file)) return None if resolved_archive_file == archive_file: logger.info("loading archive file {}".format(archive_file)) else: logger.info("loading archive file {} from cache at {}".format( archive_file, resolved_archive_file)) tempdir = None if os.path.isdir(resolved_archive_file): serialization_dir = resolved_archive_file else: # Extract archive to temp dir tempdir = tempfile.mkdtemp() logger.info("extracting archive file {} to temp dir {}".format( resolved_archive_file, tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: archive.extractall(tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME) config = BertConfig.from_json_file(config_file) logger.info("Model config {}".format(config)) # Instantiate model. model = cls(config, *inputs, **kwargs) if state_dict is None: weights_path = os.path.join(serialization_dir, WEIGHTS_NAME) state_dict = torch.load(weights_path) old_keys = [] new_keys = [] for key in state_dict.keys(): new_key = None if 'gamma' in key: new_key = key.replace('gamma', 'weight') if 'beta' in key: new_key = key.replace('beta', 'bias') if new_key: old_keys.append(key) new_keys.append(new_key) for old_key, new_key in zip(old_keys, new_keys): state_dict[new_key] = state_dict.pop(old_key) missing_keys = [] unexpected_keys = [] error_msgs = [] # copy state_dict so _load_from_state_dict can modify it metadata = getattr(state_dict, '_metadata', None) state_dict = state_dict.copy() if metadata is not None: state_dict._metadata = metadata def load(module, prefix=''): local_metadata = {} if metadata is None else metadata.get(prefix[:-1], {}) module._load_from_state_dict( state_dict, prefix, local_metadata, True, missing_keys, unexpected_keys, error_msgs) for name, child in module._modules.items(): if child is not None: load(child, prefix + name + '.') load(model, prefix='' if hasattr(model, 'bert') else 'bert.') if len(missing_keys) > 0: logger.info("Weights of {} not initialized from pretrained model: {}".format( model.__class__.__name__, missing_keys)) if len(unexpected_keys) > 0: logger.info("Weights from pretrained model not used in {}: {}".format( model.__class__.__name__, unexpected_keys)) if tempdir: # Clean up temp dir shutil.rmtree(tempdir) return model class BertModel(PreTrainedBertModel): """BERT model ("Bidirectional Embedding Representations from a Transformer"). Params: config: a BertConfig class instance with the configuration to build a new model Inputs: `input_ids`: a torch.LongTensor of shape [batch_size, sequence_length] with the word token indices in the vocabulary(see the tokens preprocessing logic in the scripts `extract_features.py`, `run_classifier.py` and `run_squad.py`) `token_type_ids`: an optional torch.LongTensor of shape [batch_size, sequence_length] with the token types indices selected in [0, 1]. Type 0 corresponds to a `sentence A` and type 1 corresponds to a `sentence B` token (see BERT paper for more details). `attention_mask`: an optional torch.LongTensor of shape [batch_size, sequence_length] with indices selected in [0, 1]. It's a mask to be used if the input sequence length is smaller than the max input sequence length in the current batch. It's the mask that we typically use for attention when a batch has varying length sentences. `output_all_encoded_layers`: boolean which controls the content of the `encoded_layers` output as described below. Default: `True`. Outputs: Tuple of (encoded_layers, pooled_output) `encoded_layers`: controled by `output_all_encoded_layers` argument: - `output_all_encoded_layers=True`: outputs a list of the full sequences of encoded-hidden-states at the end of each attention block (i.e. 12 full sequences for BERT-base, 24 for BERT-large), each encoded-hidden-state is a torch.FloatTensor of size [batch_size, sequence_length, hidden_size], - `output_all_encoded_layers=False`: outputs only the full sequence of hidden-states corresponding to the last attention block of shape [batch_size, sequence_length, hidden_size], `pooled_output`: a torch.FloatTensor of size [batch_size, hidden_size] which is the output of a classifier pretrained on top of the hidden state associated to the first character of the input (`CLF`) to train on the Next-Sentence task (see BERT's paper). Example usage: ```python # Already been converted into WordPiece token ids input_ids = torch.LongTensor([[31, 51, 99], [15, 5, 0]]) input_mask = torch.LongTensor([[1, 1, 1], [1, 1, 0]]) token_type_ids = torch.LongTensor([[0, 0, 1], [0, 1, 0]]) config = modeling.BertConfig(vocab_size_or_config_json_file=32000, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072) model = modeling.BertModel(config=config) all_encoder_layers, pooled_output = model(input_ids, token_type_ids, input_mask) ``` """ def __init__(self, config, remove_head=False, remove_pooled=False, no_nsp=False): super(BertModel, self).__init__(config, remove_head) self.embeddings = BertEmbeddings(config) self.encoder = BertEncoder(config) if not remove_head: if no_nsp: self.pooler = None else: self.pooler = BertPooler(config) else: if not remove_pooled and not no_nsp: self.pooler = BertPooler(config) else: self.pooler = None self.apply(self.init_bert_weights) def forward(self, input_ids, token_type_ids=None, attention_mask=None, output_all_encoded_layers=True): if attention_mask is None: attention_mask = torch.ones_like(input_ids) if token_type_ids is None: token_type_ids = torch.zeros_like(input_ids) # We create a 3D attention mask from a 2D tensor mask. # Sizes are [batch_size, 1, 1, to_seq_length] # So we can broadcast to [batch_size, num_heads, from_seq_length, to_seq_length] # this attention mask is more simple than the triangular masking of causal attention # used in OpenAI GPT, we just need to prepare the broadcast dimension here. extended_attention_mask = attention_mask.unsqueeze(1).unsqueeze(2) # Since attention_mask is 1.0 for positions we want to attend and 0.0 for # masked positions, this operation will create a tensor which is 0.0 for # positions we want to attend and -10000.0 for masked positions. # Since we are adding it to the raw scores before the softmax, this is # effectively the same as removing these entirely. extended_attention_mask = extended_attention_mask.to(dtype=next(self.parameters()).dtype) # fp16 compatibility - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - pretraining/fairseq/models/pair_bert.py [440:647]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - class PreTrainedBertModel(nn.Module): """ An abstract class to handle weights initialization and a simple interface for dowloading and loading pretrained models. """ def __init__(self, config, *inputs, **kwargs): super(PreTrainedBertModel, self).__init__() if not isinstance(config, BertConfig): raise ValueError( "Parameter config in `{}(config)` should be an instance of class `BertConfig`. " "To create a model from a Google pretrained model use " "`model = {}.from_pretrained(PRETRAINED_MODEL_NAME)`".format( self.__class__.__name__, self.__class__.__name__ )) self.config = config def init_bert_weights(self, module): """ Initialize the weights. """ if isinstance(module, (nn.Linear, nn.Embedding)): # Slightly different from the TF version which uses truncated_normal for initialization # cf https://github.com/pytorch/pytorch/pull/5617 module.weight.data.normal_(mean=0.0, std=self.config.initializer_range) elif isinstance(module, BertLayerNorm): module.beta.data.zero_() module.gamma.data.fill_(1.0) if isinstance(module, nn.Linear) and module.bias is not None: module.bias.data.zero_() @classmethod def from_pretrained(cls, pretrained_model_name, state_dict=None, cache_dir=None, *inputs, **kwargs): """ Instantiate a PreTrainedBertModel from a pre-trained model file or a pytorch state dict. Download and cache the pre-trained model file if needed. Params: pretrained_model_name: either: - a str with the name of a pre-trained model to load selected in the list of: . `bert-base-uncased` . `bert-large-uncased` . `bert-base-cased` . `bert-large-cased` . `bert-base-multilingual-uncased` . `bert-base-multilingual-cased` . `bert-base-chinese` - a path or url to a pretrained model archive containing: . `bert_config.json` a configuration file for the model . `pytorch_model.bin` a PyTorch dump of a BertForPreTraining instance cache_dir: an optional path to a folder in which the pre-trained models will be cached. state_dict: an optional state dictionnary (collections.OrderedDict object) to use instead of Google pre-trained models *inputs, **kwargs: additional input for the specific Bert class (ex: num_labels for BertForSequenceClassification) """ if pretrained_model_name in PRETRAINED_MODEL_ARCHIVE_MAP: archive_file = PRETRAINED_MODEL_ARCHIVE_MAP[pretrained_model_name] else: archive_file = pretrained_model_name # redirect to the cache, if necessary try: resolved_archive_file = cached_path(archive_file, cache_dir=cache_dir) except FileNotFoundError: logger.error( "Model name '{}' was not found in model name list ({}). " "We assumed '{}' was a path or url but couldn't find any file " "associated to this path or url.".format( pretrained_model_name, ', '.join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()), archive_file)) return None if resolved_archive_file == archive_file: logger.info("loading archive file {}".format(archive_file)) else: logger.info("loading archive file {} from cache at {}".format( archive_file, resolved_archive_file)) tempdir = None if os.path.isdir(resolved_archive_file): serialization_dir = resolved_archive_file else: # Extract archive to temp dir tempdir = tempfile.mkdtemp() logger.info("extracting archive file {} to temp dir {}".format( resolved_archive_file, tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: archive.extractall(tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME) config = BertConfig.from_json_file(config_file) logger.info("Model config {}".format(config)) # Instantiate model. model = cls(config, *inputs, **kwargs) if state_dict is None: weights_path = os.path.join(serialization_dir, WEIGHTS_NAME) state_dict = torch.load(weights_path) old_keys = [] new_keys = [] for key in state_dict.keys(): new_key = None if 'gamma' in key: new_key = key.replace('gamma', 'weight') if 'beta' in key: new_key = key.replace('beta', 'bias') if new_key: old_keys.append(key) new_keys.append(new_key) for old_key, new_key in zip(old_keys, new_keys): state_dict[new_key] = state_dict.pop(old_key) missing_keys = [] unexpected_keys = [] error_msgs = [] # copy state_dict so _load_from_state_dict can modify it metadata = getattr(state_dict, '_metadata', None) state_dict = state_dict.copy() if metadata is not None: state_dict._metadata = metadata def load(module, prefix=''): local_metadata = {} if metadata is None else metadata.get(prefix[:-1], {}) module._load_from_state_dict( state_dict, prefix, local_metadata, True, missing_keys, unexpected_keys, error_msgs) for name, child in module._modules.items(): if child is not None: load(child, prefix + name + '.') load(model, prefix='' if hasattr(model, 'bert') else 'bert.') if len(missing_keys) > 0: logger.info("Weights of {} not initialized from pretrained model: {}".format( model.__class__.__name__, missing_keys)) if len(unexpected_keys) > 0: logger.info("Weights from pretrained model not used in {}: {}".format( model.__class__.__name__, unexpected_keys)) if tempdir: # Clean up temp dir shutil.rmtree(tempdir) return model class BertModel(PreTrainedBertModel): """BERT model ("Bidirectional Embedding Representations from a Transformer"). Params: config: a BertConfig class instance with the configuration to build a new model Inputs: `input_ids`: a torch.LongTensor of shape [batch_size, sequence_length] with the word token indices in the vocabulary(see the tokens preprocessing logic in the scripts `extract_features.py`, `run_classifier.py` and `run_squad.py`) `token_type_ids`: an optional torch.LongTensor of shape [batch_size, sequence_length] with the token types indices selected in [0, 1]. Type 0 corresponds to a `sentence A` and type 1 corresponds to a `sentence B` token (see BERT paper for more details). `attention_mask`: an optional torch.LongTensor of shape [batch_size, sequence_length] with indices selected in [0, 1]. It's a mask to be used if the input sequence length is smaller than the max input sequence length in the current batch. It's the mask that we typically use for attention when a batch has varying length sentences. `output_all_encoded_layers`: boolean which controls the content of the `encoded_layers` output as described below. Default: `True`. Outputs: Tuple of (encoded_layers, pooled_output) `encoded_layers`: controled by `output_all_encoded_layers` argument: - `output_all_encoded_layers=True`: outputs a list of the full sequences of encoded-hidden-states at the end of each attention block (i.e. 12 full sequences for BERT-base, 24 for BERT-large), each encoded-hidden-state is a torch.FloatTensor of size [batch_size, sequence_length, hidden_size], - `output_all_encoded_layers=False`: outputs only the full sequence of hidden-states corresponding to the last attention block of shape [batch_size, sequence_length, hidden_size], `pooled_output`: a torch.FloatTensor of size [batch_size, hidden_size] which is the output of a classifier pretrained on top of the hidden state associated to the first character of the input (`CLF`) to train on the Next-Sentence task (see BERT's paper). Example usage: ```python # Already been converted into WordPiece token ids input_ids = torch.LongTensor([[31, 51, 99], [15, 5, 0]]) input_mask = torch.LongTensor([[1, 1, 1], [1, 1, 0]]) token_type_ids = torch.LongTensor([[0, 0, 1], [0, 1, 0]]) config = modeling.BertConfig(vocab_size_or_config_json_file=32000, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072) model = modeling.BertModel(config=config) all_encoder_layers, pooled_output = model(input_ids, token_type_ids, input_mask) ``` """ def __init__(self, config, remove_head=False, remove_pooled=False, no_nsp=False): super(BertModel, self).__init__(config, remove_head) self.embeddings = BertEmbeddings(config) self.encoder = BertEncoder(config) if not remove_head: if no_nsp: self.pooler = None else: self.pooler = BertPooler(config) else: if not remove_pooled and not no_nsp: self.pooler = BertPooler(config) else: self.pooler = None self.apply(self.init_bert_weights) def forward(self, input_ids, token_type_ids=None, attention_mask=None, output_all_encoded_layers=True): if attention_mask is None: attention_mask = torch.ones_like(input_ids) if token_type_ids is None: token_type_ids = torch.zeros_like(input_ids) # We create a 3D attention mask from a 2D tensor mask. # Sizes are [batch_size, 1, 1, to_seq_length] # So we can broadcast to [batch_size, num_heads, from_seq_length, to_seq_length] # this attention mask is more simple than the triangular masking of causal attention # used in OpenAI GPT, we just need to prepare the broadcast dimension here. extended_attention_mask = attention_mask.unsqueeze(1).unsqueeze(2) # Since attention_mask is 1.0 for positions we want to attend and 0.0 for # masked positions, this operation will create a tensor which is 0.0 for # positions we want to attend and -10000.0 for masked positions. # Since we are adding it to the raw scores before the softmax, this is # effectively the same as removing these entirely. extended_attention_mask = extended_attention_mask.to(dtype=next(self.parameters()).dtype) # fp16 compatibility - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -