def __init__()

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

• 17 lines of code
• 3 McCabe index (conditional complexity)

    def __init__(self, config: DeepseekV2Config):
        super().__init__(config)
        self.padding_idx = config.pad_token_id
        self.vocab_size = config.vocab_size

        self.embed_tokens = nn.Embedding(
            config.vocab_size, config.hidden_size, self.padding_idx
        )
        self.layers = nn.ModuleList(
            [
                DeepseekV2DecoderLayer(config, layer_idx)
                for layer_idx in range(config.num_hidden_layers)
            ]
        )
        self._use_flash_attention_2 = config._attn_implementation == "flash_attention_2"
        self.norm = DeepseekV2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)

        self.gradient_checkpointing = False
        # Initialize weights and apply final processing
        self.post_init()