def __init__()

in deepseek_vl2/models/modeling_deepseek_vl_v2.py [0:0]

• 29 lines of code
• 8 McCabe index (conditional complexity)

    def __init__(self, cfg):

        super().__init__()

        self.cfg = cfg

        if cfg.projector_type == "identity":
            modules = nn.Identity()

        elif cfg.projector_type == "linear":
            modules = nn.Linear(cfg.input_dim, cfg.n_embed)

        elif cfg.projector_type == "mlp_gelu":
            mlp_depth = cfg.depth
            modules = [nn.Linear(cfg.input_dim, cfg.n_embed)]
            for _ in range(1, mlp_depth):
                modules.append(nn.GELU())
                modules.append(nn.Linear(cfg.n_embed, cfg.n_embed))
            modules = nn.Sequential(*modules)

        elif cfg.projector_type == "downsample_mlp_gelu":
            mlp_depth = cfg.depth
            mlp_ratio = cfg.mlp_ratio
            modules = [nn.Linear(cfg.input_dim * cfg.downsample_ratio * cfg.downsample_ratio, cfg.n_embed * mlp_ratio)]
            for _ in range(1, mlp_depth - 1):
                modules.append(nn.GELU())
                modules.append(nn.Linear(cfg.n_embed * mlp_ratio, cfg.n_embed * mlp_ratio))
            modules.append(nn.GELU())
            modules.append(nn.Linear(cfg.n_embed * mlp_ratio, cfg.n_embed))
            modules = nn.Sequential(*modules)

        else:
            raise ValueError(f"Unknown projector type: {cfg.projector_type}")

        if cfg.token_pooling:
            self.token_pooling_layer = nn.Linear(cfg.input_dim * 4, cfg.input_dim)

        self.layers = modules