raise ValueError("Need to provide either `input_ids` or `input_embeds`.") input_shape = shape_list(inputs_embeds)[:-1] if token_type_ids is None: token_type_ids = tf.fill(dims=input_shape, value=0) if position_ids is None: position_ids = tf.expand_dims( tf.range(start=past_k...
embedding_output = self.embeddings( input_ids=input_ids, position_ids=position_ids, token_type_ids=token_type_ids, inputs_embeds=inputs_embeds, past_key_values_length=past_key_values_length, ) encoder_outputs = self.encoder( embedding_output, # 从这儿能看到,Encoder接收的是embeddings的输出,进...
if token_type_ids is None: token_type_ids = torch.zeros(input_shape, dtype=torch.long, device=self.position_ids.device) if inputs_embeds is None: inputs_embeds = self.word_embeddings(input_ids) position_embeddings = self.position_embeddings(position_ids) token_type_embeddings = self.token...
input_ids:Optional[torch.Tensor] =None, attention_mask:Optional[torch.Tensor] =None, token_type_ids:Optional[torch.Tensor] =None, position_ids:Optional[torch.Tensor] =None, head_mask:Optional[torch.Tensor] =None, inputs_embeds:Optional[torch.Tensor] =None, labels:Optional[torch.Tensor] =None...
raise ValueError("Need to provide either `input_ids` or `input_embeds`.") input_shape = shape_list(inputs_embeds)[:-1] if token_type_ids is None: token_type_ids = tf.fill(dims=input_shape, value=0) if position_ids is None: ...
input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids, position_ids=position_ids, head_mask=head_mask, inputs_embeds=inputs_embeds, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict, ...
input_ids=None, attention_mask=None, token_type_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,
input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids, position_ids=position_ids, head_mask=head_mask, inputs_embeds=inputs_embeds, encoder_hidden_states=encoder_hidden_states, encoder_attention_mask=encoder_attention_mask, ...
Tensor] = None,inputs_embeds: typing.Optional[torch.Tensor] = None,encoder_hidden_states: typing.Optional[torch.Tensor] = None,encoder_attention_mask: typing.Optional[torch.Tensor] = None,past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None,use_cache: typing.Optional[bool]...
input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, next_sentence_label=None, output_attentions=None, output_hidden_states=None, return_dict=None, ): ...