optimum/bettertransformer/models/encoder_models.py [120:147]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                attention_mask = torch.reshape(attention_mask, (attention_mask.shape[0], attention_mask.shape[-1]))
                hidden_states = torch._nested_tensor_from_mask(hidden_states, ~attention_mask)
                attention_mask = None

            hidden_states = torch._transformer_encoder_layer_fwd(
                hidden_states,
                self.embed_dim,
                self.num_heads,
                self.in_proj_weight,
                self.in_proj_bias,
                self.out_proj_weight,
                self.out_proj_bias,
                self.use_gelu,
                self.norm_first,
                self.norm1_eps,
                self.norm1_weight,
                self.norm1_bias,
                self.norm2_weight,
                self.norm2_bias,
                self.linear1_weight,
                self.linear1_bias,
                self.linear2_weight,
                self.linear2_bias,
                attention_mask,
            )
            if hidden_states.is_nested and self.is_last_layer:
                hidden_states = hidden_states.to_padded_tensor(0.0)
        else:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/bettertransformer/models/encoder_models.py [1295:1322]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                attention_mask = torch.reshape(attention_mask, (attention_mask.shape[0], attention_mask.shape[-1]))
                hidden_states = torch._nested_tensor_from_mask(hidden_states, ~attention_mask)
                attention_mask = None

            hidden_states = torch._transformer_encoder_layer_fwd(
                hidden_states,
                self.embed_dim,
                self.num_heads,
                self.in_proj_weight,
                self.in_proj_bias,
                self.out_proj_weight,
                self.out_proj_bias,
                self.use_gelu,
                self.norm_first,
                self.norm1_eps,
                self.norm1_weight,
                self.norm1_bias,
                self.norm2_weight,
                self.norm2_bias,
                self.linear1_weight,
                self.linear1_bias,
                self.linear2_weight,
                self.linear2_bias,
                attention_mask,
            )
            if hidden_states.is_nested and self.is_last_layer:
                hidden_states = hidden_states.to_padded_tensor(0.0)
        else:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -