from bidirectional_mistral import MistralBiModel from transformers import MistralPreTrainedModel import torch import numpy as np from typing import Optional, List from torch import nn from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss from transformers.modeling_outputs import SequenceClassifierOutputWithPast class MistralForSequenceClassification(MistralPreTrainedModel): def __init__(self, config): super().__init__(config) self.num_labels = config.num_labels self.model = MistralBiModel(config) self.score = nn.Linear(config.hidden_size, self.num_labels, bias=False) # Initialize weights and apply final processing self.post_init() def forward( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_values: Optional[List[torch.FloatTensor]] = None, inputs_embeds: Optional[torch.FloatTensor] = None, labels: Optional[torch.LongTensor] = None, use_cache: Optional[bool] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, token_type_ids: Optional[bool] = None ): r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy). """ return_dict = return_dict if return_dict is not None else self.config.use_return_dict transformer_outputs = self.model( input_ids, attention_mask=attention_mask, position_ids=position_ids, past_key_values=past_key_values, inputs_embeds=inputs_embeds, use_cache=use_cache, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict, ) pooled_output = transformer_outputs[0][:, 0] logits = self.score(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,) + transformer_outputs[2:] return ((loss,) + output) if loss is not None else output return SequenceClassifierOutputWithPast( loss=loss, logits=logits, past_key_values=transformer_outputs.past_key_values, hidden_states=transformer_outputs.hidden_states, attentions=transformer_outputs.attentions, )