from transformers.models.bert.modeling_bert import BertEncoder, BertPooler, BertEmbeddings, BaseModelOutputWithPoolingAndCrossAttentions from transformers import BertModel import torch class BertEmbeddingsV2(BertEmbeddings): def __init__(self, config): super().__init__(config) self.pad_token_id = config.pad_token_id self.word_embeddings = torch.nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=self.pad_token_id) self.position_embeddings = torch.nn.Embedding(config.max_position_embeddings, config.hidden_size, padding_idx=0) # here padding_idx is always 0 self.LayerNorm = torch.nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) self.dropout = torch.nn.Dropout(config.hidden_dropout_prob) def forward(self, input_ids=None, pos_tag_ids=None, token_type_ids=None, position_ids=None, inputs_embeds=None, past_key_values_length=0): inputs_embeds = self.word_embeddings(input_ids) position_ids = self.create_position_ids_from_input_ids(input_ids) position_embeddings = self.position_embeddings(position_ids) embeddings = inputs_embeds + position_embeddings return self.dropout(self.LayerNorm(embeddings)) def create_position_ids_from_input_ids(self, input_ids): mask = input_ids.ne(self.pad_token_id).int() return torch.cumsum(mask, dim=1).long() * mask class BertModelV2(BertModel): def __init__(self, config): super().__init__(config) self.config = config self.embeddings = BertEmbeddingsV2(config) self.encoder = BertEncoder(config) self.pooler = BertPooler(config) if config.add_pooling_layer else None self.init_weights() def forward( self, input_ids=None, attention_mask=None, token_type_ids=None, pos_tag_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, encoder_hidden_states=None, encoder_attention_mask=None, past_key_values=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None, ): r""" encoder_hidden_states (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`): Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder. encoder_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`): Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in ``[0, 1]``: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. past_key_values (:obj:`tuple(tuple(torch.FloatTensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`): Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If :obj:`past_key_values` are used, the user can optionally input only the last :obj:`decoder_input_ids` (those that don't have their past key value states given to this model) of shape :obj:`(batch_size, 1)` instead of all :obj:`decoder_input_ids` of shape :obj:`(batch_size, sequence_length)`. use_cache (:obj:`bool`, `optional`): If set to :obj:`True`, :obj:`past_key_values` key value states are returned and can be used to speed up decoding (see :obj:`past_key_values`). """ output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions output_hidden_states = ( output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states ) return_dict = return_dict if return_dict is not None else self.config.use_return_dict if self.config.is_decoder: use_cache = use_cache if use_cache is not None else self.config.use_cache else: use_cache = False if input_ids is not None and inputs_embeds is not None: raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time") elif input_ids is not None: input_shape = input_ids.size() batch_size, seq_length = input_shape elif inputs_embeds is not None: input_shape = inputs_embeds.size()[:-1] batch_size, seq_length = input_shape else: raise ValueError("You have to specify either input_ids or inputs_embeds") device = input_ids.device if input_ids is not None else inputs_embeds.device # past_key_values_length past_key_values_length = past_key_values[0][0].shape[2] if past_key_values is not None else 0 if attention_mask is None: attention_mask = torch.ones(((batch_size, seq_length + past_key_values_length)), device=device) if token_type_ids is None: token_type_ids = torch.zeros(input_shape, dtype=torch.long, device=device) # We can provide a self-attention mask of dimensions [batch_size, from_seq_length, to_seq_length] # ourselves in which case we just need to make it broadcastable to all heads. extended_attention_mask: torch.Tensor = self.get_extended_attention_mask(attention_mask, input_shape, device) # If a 2D or 3D attention mask is provided for the cross-attention # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length] if self.config.is_decoder and encoder_hidden_states is not None: encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.size() encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length) if encoder_attention_mask is None: encoder_attention_mask = torch.ones(encoder_hidden_shape, device=device) encoder_extended_attention_mask = self.invert_attention_mask(encoder_attention_mask) else: encoder_extended_attention_mask = None # Prepare head mask if needed # 1.0 in head_mask indicate we keep the head # attention_probs has shape bsz x n_heads x N x N # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads] # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length] head_mask = self.get_head_mask(head_mask, self.config.num_hidden_layers) embedding_output = self.embeddings( input_ids=input_ids, position_ids=position_ids, token_type_ids=token_type_ids, pos_tag_ids=pos_tag_ids, inputs_embeds=inputs_embeds, past_key_values_length=past_key_values_length, ) encoder_outputs = self.encoder( embedding_output, attention_mask=extended_attention_mask, head_mask=head_mask, encoder_hidden_states=encoder_hidden_states, encoder_attention_mask=encoder_extended_attention_mask, past_key_values=past_key_values, use_cache=use_cache, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict, ) sequence_output = encoder_outputs[0] pooled_output = self.pooler(sequence_output) if self.pooler is not None else None if not return_dict: return (sequence_output, pooled_output) + encoder_outputs[1:] return BaseModelOutputWithPoolingAndCrossAttentions( last_hidden_state=sequence_output, pooler_output=pooled_output, past_key_values=encoder_outputs.past_key_values, hidden_states=encoder_outputs.hidden_states, attentions=encoder_outputs.attentions, cross_attentions=encoder_outputs.cross_attentions, )