from typing import List, Optional, Tuple, Union import math import torch import torch.utils.checkpoint from mmengine.logging import MMLogger from torch import nn from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss from transformers import PreTrainedModel from transformers.activations import ACT2FN from transformers.modeling_outputs import ( BaseModelOutputWithPastAndCrossAttentions, BaseModelOutputWithPoolingAndCrossAttentions, SequenceClassifierOutput, TokenClassifierOutput, ) from transformers.pytorch_utils import apply_chunking_to_forward, find_pruneable_heads_and_indices, prune_linear_layer from .configuration_bert import MyBertConfig logger = MMLogger.get_current_instance() class BertEmbeddings(nn.Module): def __init__(self, config): super().__init__() self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=config.pad_token_id) self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size) self.token_type_embeddings = nn.Embedding(config.type_vocab_size, config.hidden_size) # self.LayerNorm is not snake-cased to stick with TensorFlow model variable name and be able to load # any TensorFlow checkpoint file self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) self.dropout = nn.Dropout(config.hidden_dropout_prob) # position_ids (1, len position emb) is contiguous in memory and exported when serialized self.position_embedding_type = getattr(config, "position_embedding_type", "absolute") self.register_buffer("position_ids", torch.arange(config.max_position_embeddings).expand((1, -1))) self.register_buffer( "token_type_ids", torch.zeros(self.position_ids.size(), dtype=torch.long), persistent=False ) def forward( self, input_ids: Optional[torch.LongTensor] = None, token_type_ids: Optional[torch.LongTensor] = None, position_ids: Optional[torch.LongTensor] = None, inputs_embeds: Optional[torch.FloatTensor] = None, past_key_values_length: int = 0, ) -> torch.Tensor: if input_ids is not None: input_shape = input_ids.size() else: input_shape = inputs_embeds.size()[:-1] seq_length = input_shape[1] if position_ids is None: position_ids = self.position_ids[:, past_key_values_length: seq_length + past_key_values_length] # Setting the token_type_ids to the registered buffer in constructor where it is all zeros, which usually occurs # when its auto-generated, registered buffer helps users when tracing the model without passing token_type_ids, solves # issue #5664 if token_type_ids is None: if hasattr(self, "token_type_ids"): buffered_token_type_ids = self.token_type_ids[:, :seq_length] buffered_token_type_ids_expanded = buffered_token_type_ids.expand(input_shape[0], seq_length) token_type_ids = buffered_token_type_ids_expanded else: 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) token_type_embeddings = self.token_type_embeddings(token_type_ids) embeddings = inputs_embeds + token_type_embeddings if self.position_embedding_type == "absolute": position_embeddings = self.position_embeddings(position_ids) embeddings += position_embeddings embeddings = self.LayerNorm(embeddings) embeddings = self.dropout(embeddings) return embeddings class BertSelfAttention(nn.Module): def __init__(self, config, position_embedding_type=None): super().__init__() if config.hidden_size % config.num_attention_heads != 0 and not hasattr(config, "embedding_size"): raise ValueError( f"The hidden size ({config.hidden_size}) is not a multiple of the number of attention " f"heads ({config.num_attention_heads})" ) self.num_attention_heads = config.num_attention_heads self.attention_head_size = int(config.hidden_size / config.num_attention_heads) self.all_head_size = self.num_attention_heads * self.attention_head_size self.query = nn.Linear(config.hidden_size, self.all_head_size) self.key = nn.Linear(config.hidden_size, self.all_head_size) self.value = nn.Linear(config.hidden_size, self.all_head_size) self.dropout = nn.Dropout(config.attention_probs_dropout_prob) self.position_embedding_type = position_embedding_type or getattr( config, "position_embedding_type", "absolute" ) if self.position_embedding_type == "relative_key" or self.position_embedding_type == "relative_key_query": self.max_position_embeddings = config.max_position_embeddings self.distance_embedding = nn.Embedding(2 * config.max_position_embeddings - 1, self.attention_head_size) self.is_decoder = config.is_decoder def transpose_for_scores(self, x: torch.Tensor) -> torch.Tensor: new_x_shape = x.size()[:-1] + (self.num_attention_heads, self.attention_head_size) x = x.view(new_x_shape) return x.permute(0, 2, 1, 3) def forward( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.FloatTensor] = None, head_mask: Optional[torch.FloatTensor] = None, encoder_hidden_states: Optional[torch.FloatTensor] = None, encoder_attention_mask: Optional[torch.FloatTensor] = None, past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None, output_attentions: Optional[bool] = False, ) -> Tuple[torch.Tensor]: mixed_query_layer = self.query(hidden_states) # If this is instantiated as a cross-attention module, the keys # and values come from an encoder; the attention mask needs to be # such that the encoder's padding tokens are not attended to. is_cross_attention = encoder_hidden_states is not None if is_cross_attention and past_key_value is not None: # reuse k,v, cross_attentions key_layer = past_key_value[0] value_layer = past_key_value[1] attention_mask = encoder_attention_mask elif is_cross_attention: key_layer = self.transpose_for_scores(self.key(encoder_hidden_states)) value_layer = self.transpose_for_scores(self.value(encoder_hidden_states)) attention_mask = encoder_attention_mask elif past_key_value is not None: key_layer = self.transpose_for_scores(self.key(hidden_states)) value_layer = self.transpose_for_scores(self.value(hidden_states)) key_layer = torch.cat([past_key_value[0], key_layer], dim=2) value_layer = torch.cat([past_key_value[1], value_layer], dim=2) else: key_layer = self.transpose_for_scores(self.key(hidden_states)) value_layer = self.transpose_for_scores(self.value(hidden_states)) query_layer = self.transpose_for_scores(mixed_query_layer) use_cache = past_key_value is not None if self.is_decoder: # if cross_attention save Tuple(torch.Tensor, torch.Tensor) of all cross attention key/value_states. # Further calls to cross_attention layer can then reuse all cross-attention # key/value_states (first "if" case) # if uni-directional self-attention (decoder) save Tuple(torch.Tensor, torch.Tensor) of # all previous decoder key/value_states. Further calls to uni-directional self-attention # can concat previous decoder key/value_states to current projected key/value_states (third "elif" case) # if encoder bi-directional self-attention `past_key_value` is always `None` past_key_value = (key_layer, value_layer) # Take the dot product between "query" and "key" to get the raw attention scores. attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2)) if self.position_embedding_type == "relative_key" or self.position_embedding_type == "relative_key_query": query_length, key_length = query_layer.shape[2], key_layer.shape[2] if use_cache: position_ids_l = torch.tensor(key_length - 1, dtype=torch.long, device=hidden_states.device).view( -1, 1 ) else: position_ids_l = torch.arange(query_length, dtype=torch.long, device=hidden_states.device).view(-1, 1) position_ids_r = torch.arange(key_length, dtype=torch.long, device=hidden_states.device).view(1, -1) distance = position_ids_l - position_ids_r positional_embedding = self.distance_embedding(distance + self.max_position_embeddings - 1) positional_embedding = positional_embedding.to(dtype=query_layer.dtype) # fp16 compatibility if self.position_embedding_type == "relative_key": relative_position_scores = torch.einsum("bhld,lrd->bhlr", query_layer, positional_embedding) attention_scores = attention_scores + relative_position_scores elif self.position_embedding_type == "relative_key_query": relative_position_scores_query = torch.einsum("bhld,lrd->bhlr", query_layer, positional_embedding) relative_position_scores_key = torch.einsum("bhrd,lrd->bhlr", key_layer, positional_embedding) attention_scores = attention_scores + relative_position_scores_query + relative_position_scores_key attention_scores = attention_scores / math.sqrt(self.attention_head_size) if attention_mask is not None: # Apply the attention mask is (precomputed for all layers in BertModel forward() function) attention_scores = attention_scores + attention_mask # Normalize the attention scores to probabilities. attention_probs = nn.functional.softmax(attention_scores, dim=-1) # This is actually dropping out entire tokens to attend to, which might # seem a bit unusual, but is taken from the original Transformer paper. attention_probs = self.dropout(attention_probs) # Mask heads if we want to if head_mask is not None: attention_probs = attention_probs * head_mask context_layer = torch.matmul(attention_probs, value_layer) context_layer = context_layer.permute(0, 2, 1, 3).contiguous() new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,) context_layer = context_layer.view(new_context_layer_shape) outputs = (context_layer, attention_probs) if output_attentions else (context_layer,) if self.is_decoder: outputs = outputs + (past_key_value,) return outputs class BertSelfOutput(nn.Module): def __init__(self, config): super().__init__() self.dense = nn.Linear(config.hidden_size, config.hidden_size) self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) self.dropout = nn.Dropout(config.hidden_dropout_prob) def forward(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor) -> torch.Tensor: hidden_states = self.dense(hidden_states) hidden_states = self.dropout(hidden_states) hidden_states = self.LayerNorm(hidden_states + input_tensor) return hidden_states class BertAttention(nn.Module): def __init__(self, config, position_embedding_type=None): super().__init__() self.self = BertSelfAttention(config, position_embedding_type=position_embedding_type) self.output = BertSelfOutput(config) self.pruned_heads = set() def prune_heads(self, heads): if len(heads) == 0: return heads, index = find_pruneable_heads_and_indices( heads, self.self.num_attention_heads, self.self.attention_head_size, self.pruned_heads ) # Prune linear layers self.self.query = prune_linear_layer(self.self.query, index) self.self.key = prune_linear_layer(self.self.key, index) self.self.value = prune_linear_layer(self.self.value, index) self.output.dense = prune_linear_layer(self.output.dense, index, dim=1) # Update hyper params and store pruned heads self.self.num_attention_heads = self.self.num_attention_heads - len(heads) self.self.all_head_size = self.self.attention_head_size * self.self.num_attention_heads self.pruned_heads = self.pruned_heads.union(heads) def forward( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.FloatTensor] = None, head_mask: Optional[torch.FloatTensor] = None, encoder_hidden_states: Optional[torch.FloatTensor] = None, encoder_attention_mask: Optional[torch.FloatTensor] = None, past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None, output_attentions: Optional[bool] = False, ) -> Tuple[torch.Tensor]: self_outputs = self.self( hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions, ) attention_output = self.output(self_outputs[0], hidden_states) outputs = (attention_output,) + self_outputs[1:] # add attentions if we output them return outputs class BertIntermediate(nn.Module): def __init__(self, config): super().__init__() self.dense = nn.Linear(config.hidden_size, config.intermediate_size) if isinstance(config.hidden_act, str): self.intermediate_act_fn = ACT2FN[config.hidden_act] else: self.intermediate_act_fn = config.hidden_act def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: hidden_states = self.dense(hidden_states) hidden_states = self.intermediate_act_fn(hidden_states) return hidden_states class BertOutput(nn.Module): def __init__(self, config): super().__init__() self.dense = nn.Linear(config.intermediate_size, config.hidden_size) self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) self.dropout = nn.Dropout(config.hidden_dropout_prob) def forward(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor) -> torch.Tensor: hidden_states = self.dense(hidden_states) hidden_states = self.dropout(hidden_states) hidden_states = self.LayerNorm(hidden_states + input_tensor) return hidden_states class BertLayer(nn.Module): def __init__(self, config): super().__init__() self.chunk_size_feed_forward = config.chunk_size_feed_forward self.seq_len_dim = 1 self.attention = BertAttention(config) self.is_decoder = config.is_decoder self.add_cross_attention = config.add_cross_attention if self.add_cross_attention: if not self.is_decoder: raise ValueError(f"{self} should be used as a decoder model if cross attention is added") self.crossattention = BertAttention(config, position_embedding_type="absolute") self.intermediate = BertIntermediate(config) self.output = BertOutput(config) def forward( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.FloatTensor] = None, head_mask: Optional[torch.FloatTensor] = None, encoder_hidden_states: Optional[torch.FloatTensor] = None, encoder_attention_mask: Optional[torch.FloatTensor] = None, past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None, output_attentions: Optional[bool] = False, ) -> Tuple[torch.Tensor]: # decoder uni-directional self-attention cached key/values tuple is at positions 1,2 self_attn_past_key_value = past_key_value[:2] if past_key_value is not None else None self_attention_outputs = self.attention( hidden_states, attention_mask, head_mask, output_attentions=output_attentions, past_key_value=self_attn_past_key_value, ) attention_output = self_attention_outputs[0] # if decoder, the last output is tuple of self-attn cache if self.is_decoder: outputs = self_attention_outputs[1:-1] present_key_value = self_attention_outputs[-1] else: outputs = self_attention_outputs[1:] # add self attentions if we output attention weights cross_attn_present_key_value = None if self.is_decoder and encoder_hidden_states is not None: if not hasattr(self, "crossattention"): raise ValueError( f"If `encoder_hidden_states` are passed, {self} has to be instantiated with cross-attention layers" " by setting `config.add_cross_attention=True`" ) # cross_attn cached key/values tuple is at positions 3,4 of past_key_value tuple cross_attn_past_key_value = past_key_value[-2:] if past_key_value is not None else None cross_attention_outputs = self.crossattention( attention_output, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, cross_attn_past_key_value, output_attentions, ) attention_output = cross_attention_outputs[0] outputs = outputs + cross_attention_outputs[1:-1] # add cross attentions if we output attention weights # add cross-attn cache to positions 3,4 of present_key_value tuple cross_attn_present_key_value = cross_attention_outputs[-1] present_key_value = present_key_value + cross_attn_present_key_value layer_output = apply_chunking_to_forward( self.feed_forward_chunk, self.chunk_size_feed_forward, self.seq_len_dim, attention_output ) outputs = (layer_output,) + outputs # if decoder, return the attn key/values as the last output if self.is_decoder: outputs = outputs + (present_key_value,) return outputs def feed_forward_chunk(self, attention_output): intermediate_output = self.intermediate(attention_output) layer_output = self.output(intermediate_output, attention_output) return layer_output class BertEncoder(nn.Module): def __init__(self, config): super().__init__() self.config = config self.layer = nn.ModuleList([BertLayer(config) for _ in range(config.num_hidden_layers)]) self.gradient_checkpointing = False def forward( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.FloatTensor] = None, head_mask: Optional[torch.FloatTensor] = None, encoder_hidden_states: Optional[torch.FloatTensor] = None, encoder_attention_mask: Optional[torch.FloatTensor] = None, past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None, use_cache: Optional[bool] = None, output_attentions: Optional[bool] = False, output_hidden_states: Optional[bool] = False, return_dict: Optional[bool] = True, ) -> Union[Tuple[torch.Tensor], BaseModelOutputWithPastAndCrossAttentions]: all_hidden_states = () if output_hidden_states else None all_self_attentions = () if output_attentions else None all_cross_attentions = () if output_attentions and self.config.add_cross_attention else None next_decoder_cache = () if use_cache else None for i, layer_module in enumerate(self.layer): if output_hidden_states: all_hidden_states = all_hidden_states + (hidden_states,) layer_head_mask = head_mask[i] if head_mask is not None else None past_key_value = past_key_values[i] if past_key_values is not None else None if self.gradient_checkpointing and self.training: if use_cache: logger.warning( "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..." ) use_cache = False def create_custom_forward(module): def custom_forward(*inputs): return module(*inputs, past_key_value, output_attentions) return custom_forward layer_outputs = torch.utils.checkpoint.checkpoint( create_custom_forward(layer_module), hidden_states, attention_mask, layer_head_mask, encoder_hidden_states, encoder_attention_mask, ) else: layer_outputs = layer_module( hidden_states, attention_mask, layer_head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions, ) hidden_states = layer_outputs[0] if use_cache: next_decoder_cache += (layer_outputs[-1],) if output_attentions: all_self_attentions = all_self_attentions + (layer_outputs[1],) if self.config.add_cross_attention: all_cross_attentions = all_cross_attentions + (layer_outputs[2],) if output_hidden_states: all_hidden_states = all_hidden_states + (hidden_states,) if not return_dict: return tuple( v for v in [ hidden_states, next_decoder_cache, all_hidden_states, all_self_attentions, all_cross_attentions, ] if v is not None ) return BaseModelOutputWithPastAndCrossAttentions( last_hidden_state=hidden_states, past_key_values=next_decoder_cache, hidden_states=all_hidden_states, attentions=all_self_attentions, cross_attentions=all_cross_attentions, ) class BertPooler(nn.Module): def __init__(self, config): super().__init__() self.dense = nn.Linear(config.hidden_size, config.hidden_size) self.activation = nn.Tanh() def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: # We "pool" the model by simply taking the hidden state corresponding # to the first token. first_token_tensor = hidden_states[:, 0] pooled_output = self.dense(first_token_tensor) pooled_output = self.activation(pooled_output) return pooled_output class BertPreTrainedModel(PreTrainedModel): config_class = MyBertConfig base_model_prefix = "bert" supports_gradient_checkpointing = True _keys_to_ignore_on_load_missing = [r"position_ids"] def _init_weights(self, module): """Initialize the weights""" if isinstance(module, nn.Linear): # 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) if module.bias is not None: module.bias.data.zero_() elif isinstance(module, nn.Embedding): module.weight.data.normal_(mean=0.0, std=self.config.initializer_range) if module.padding_idx is not None: module.weight.data[module.padding_idx].zero_() elif isinstance(module, nn.LayerNorm): module.bias.data.zero_() module.weight.data.fill_(1.0) def _set_gradient_checkpointing(self, module, value=False): if isinstance(module, BertEncoder): module.gradient_checkpointing = value class MyBertModel(BertPreTrainedModel): def __init__(self, config, add_pooling_layer=True): super().__init__(config) self.config = config self.embeddings = BertEmbeddings(config) self.encoder = BertEncoder(config) self.pooler = BertPooler(config) if add_pooling_layer else None # Initialize weights and apply final processing self.post_init() def get_input_embeddings(self): return self.embeddings.word_embeddings def set_input_embeddings(self, value): self.embeddings.word_embeddings = value def _prune_heads(self, heads_to_prune): for layer, heads in heads_to_prune.items(): self.encoder.layer[layer].attention.prune_heads(heads) def forward( self, 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, encoder_hidden_states: Optional[torch.Tensor] = None, encoder_attention_mask: Optional[torch.Tensor] = None, past_key_values: Optional[List[torch.FloatTensor]] = None, use_cache: Optional[bool] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, ) -> Union[Tuple[torch.Tensor], BaseModelOutputWithPoolingAndCrossAttentions]: 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() elif inputs_embeds is not None: input_shape = inputs_embeds.size()[:-1] else: raise ValueError("You have to specify either input_ids or inputs_embeds") batch_size, seq_length = input_shape 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: if hasattr(self.embeddings, "token_type_ids"): buffered_token_type_ids = self.embeddings.token_type_ids[:, :seq_length] buffered_token_type_ids_expanded = buffered_token_type_ids.expand(batch_size, seq_length) token_type_ids = buffered_token_type_ids_expanded else: 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) # 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, 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, ) class MyBertForSequenceClassification(BertPreTrainedModel): def __init__(self, config): super().__init__(config) self.num_labels = config.num_labels self.config = config self.bert = MyBertModel(config) classifier_dropout = ( config.classifier_dropout if config.classifier_dropout is not None else config.hidden_dropout_prob ) self.dropout = nn.Dropout(classifier_dropout) self.classifier = nn.Linear(config.hidden_size, config.num_labels) # Initialize weights and apply final processing self.post_init() def forward( self, 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, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, ) -> Union[Tuple[torch.Tensor], SequenceClassifierOutput]: return_dict = return_dict if return_dict is not None else self.config.use_return_dict outputs = self.bert( 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, ) pooled_output = outputs[1] pooled_output = self.dropout(pooled_output) logits = self.classifier(pooled_output) loss = None if labels is not None: if self.config.problem_type is None: if self.num_labels == 1: self.config.problem_type = "regression" elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int): self.config.problem_type = "single_label_classification" else: self.config.problem_type = "multi_label_classification" if self.config.problem_type == "regression": loss_fct = MSELoss() if self.num_labels == 1: loss = loss_fct(logits.squeeze(), labels.squeeze()) else: loss = loss_fct(logits, labels) elif self.config.problem_type == "single_label_classification": loss_fct = CrossEntropyLoss() loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1)) elif self.config.problem_type == "multi_label_classification": loss_fct = BCEWithLogitsLoss() loss = loss_fct(logits, labels) if not return_dict: output = (logits,) + outputs[2:] return ((loss,) + output) if loss is not None else output return SequenceClassifierOutput( loss=loss, logits=logits, hidden_states=outputs.hidden_states, attentions=outputs.attentions, ) from mmengine.model import BaseModel from nami.registry import MODELS from mmengine.registry import MODELS as MMENGINE_MODELS @MODELS.register_module() class MyBertForTokenClassification(BertPreTrainedModel, BaseModel): _keys_to_ignore_on_load_unexpected = [r"pooler"] def __init__(self, config, *args, **kwargs): # data_preprocessor = kwargs.pop('data_preprocessor', None) super().__init__(config, kwargs) # BertPreTrainedModel.__init__(self, config) # self.data_preprocessor = MMENGINE_MODELS.build(data_preprocessor) # BaseModel.__init__(self, data_preprocessor) self.num_labels = config.num_labels self.bert = MyBertModel(config, add_pooling_layer=False) classifier_dropout = ( config.classifier_dropout if config.classifier_dropout is not None else config.hidden_dropout_prob ) self.dropout = nn.Dropout(classifier_dropout) self.classifier = nn.Sequential(nn.Linear(config.hidden_size, config.hidden_size), nn.Linear(config.hidden_size, config.num_labels)) # Initialize weights and apply final processing self.post_init() def forward( self, 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, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, mode: str = 'tensor', *args,**kwargs ):# -> Union[Tuple[torch.Tensor], TokenClassifierOutput]: # return_dict = return_dict if return_dict is not None else self.config.use_return_dict outputs = self.bert( 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, ) sequence_output = outputs[0] sequence_output = self.dropout(sequence_output) logits = self.classifier(sequence_output) # if mode == 'tensor': # feats = self.extract_feat(inputs) # return self.head(feats) if self.with_head else feats # elif mode == 'loss': # return self.loss(inputs, data_samples) # elif mode == 'predict': # return self.predict(inputs, data_samples) # else: # raise RuntimeError(f'Invalid mode "{mode}".') if mode == 'loss': loss_fct = CrossEntropyLoss() loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1)) return dict(loss=loss) elif mode == 'predict': return self.predict(logits, attention_mask) # loss = None # if labels is not None: # loss_fct = CrossEntropyLoss() # loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1)) # # if not return_dict: # output = (logits,) + outputs[2:] # return ((loss,) + output) if loss is not None else output # # return TokenClassifierOutput( # loss=loss, # logits=logits, # hidden_states=outputs.hidden_states, # attentions=outputs.attentions, # ) def predict(self, logits, attention_mask): id2label = self.config.id2label pred_label = [] for pred, attn_mask in zip(logits.argmax(-1).cpu().numpy(), attention_mask.cpu().numpy()): pred_label.append([id2label[p] for p, a in zip(pred, attn_mask) if a == 1]) return pred_label