Method forward

train/patch/modeling_chatglm.py:446–486

(
            self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True,
    )

        self.mlp = MLP(config, device=device)

    def forward(
            self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True,
    ):
        # hidden_states: [s, b, h]

        # Layer norm at the beginning of the transformer layer.
        layernorm_output = self.input_layernorm(hidden_states)
        # Self attention.
        attention_output, kv_cache = self.self_attention(
            layernorm_output,
            attention_mask,
            rotary_pos_emb,
            kv_cache=kv_cache,
            use_cache=use_cache
        )

        # Residual connection.
        if self.apply_residual_connection_post_layernorm:
            residual = layernorm_output
        else:
            residual = hidden_states

        layernorm_input = torch.nn.functional.dropout(attention_output, p=self.hidden_dropout, training=self.training)
        layernorm_input = residual + layernorm_input

        # Layer norm post the self attention.
        layernorm_output = self.post_attention_layernorm(layernorm_input)

        # MLP.
        mlp_output = self.mlp(layernorm_output)

        # Second residual connection.
        if self.apply_residual_connection_post_layernorm:
            residual = layernorm_output
        else:
            residual = layernorm_input

        output = torch.nn.functional.dropout(mlp_output, p=self.hidden_dropout, training=self.training)
        output = residual + output

        return output, kv_cache


class GLMTransformer(torch.nn.Module):