自定义TransformerEncoderLayer遇'is_causal'参数错误，求修复方案

问题核心是：你给自定义层的forward加了**kwargs，但没把这些参数传递给内部调用的nn.MultiheadAttention。PyTorch新版本的MultiheadAttention.forward新增了is_causal参数，TrainAD的上层逻辑会自动传递这个参数，你的自定义层接收到后没转发给注意力模块，导致报错。

直接修改forward方法里的注意力调用部分，把**kwargs传进去即可，顺便补上之前遗漏的掩码参数，让逻辑和PyTorch原生层对齐：

class TransformerEncoderLayer(nn.Module):
    def __init__(self, d_model, nhead, dim_feedforward=16, dropout=0):
        super(TransformerEncoderLayer, self).__init__()
        self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
        self.linear1 = nn.Linear(d_model, dim_feedforward)
        self.dropout = nn.Dropout(dropout)
        self.linear2 = nn.Linear(dim_feedforward, d_model)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)

        self.activation = nn.LeakyReLU(True)

    def forward(self, src, src_mask=None, src_key_padding_mask=None, **kwargs):
        # 关键修改：将所有接收的参数转发给注意力模块
        src2 = self.self_attn(src, src, src, attn_mask=src_mask, key_padding_mask=src_key_padding_mask, **kwargs)[0]
        src = src + self.dropout1(src2)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
        src = src + self.dropout2(src2)
        return src

内容的提问来源于stack exchange，提问作者23_7867