configuration_deepseek.py

"""Deepseek Moe model configuration"""
from transformers.utils import logging
from transformers.configuration_utils import PretrainedConfig
from transformers.modeling_rope_utils import rope_config_validation

logger = logging.get_logger(__name__)

DEEPSEEK_FIXES_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
class DeepseekConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a DeepseekModel`]. It is used to instantiate an DeepSeek
    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
    defaults will yield a similar configuration to that of the DeepseekModel-20b.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.


    Args:
        vocab_size (`int`, *optional*, defaults to 128256):
            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`DeepseekModel`]
        hidden_size (`int`, *optional*, defaults to 4096):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 11008):
            Dimension of the MLP representations.
        moe_intermediate_size (`int`, *optional*, defaults to 1792):
            Dimension of the MoE representations.
        num_hidden_layers (`int`, *optional*, defaults to 32):
            Number of hidden layers in the Transformer decoder.
        num_attention_heads (`int`, *optional*, defaults to 32):
            Number of attention heads for each attention layer in the Transformer decoder.
        n_shared_experts (`int`, *optional*, defaults to None):
            Number of shared experts, None means dense model.
        n_routed_experts (`int`, *optional*, defaults to None):
            Number of routed experts, None means dense model.
        num_experts_per_tok (`int`, *optional*, defaults to None):
            Number of selected experts, None means dense model.
        moe_layer_freq (`int`, *optional*, defaults to 1):
            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
        first_k_dense_replace (`int`, *optional*, defaults to 0):
            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
                                                            \--k dense layers--/
        norm_topk_prob (`bool`, *optional*, defaults to False):
            Whether to normalize the weights of the routed experts.
        scoring_func (`str`, *optional*, defaults to 'softmax'):
            Method of computing expert weights.
        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
            Auxiliary loss weight coefficient.
        seq_aux = (`bool`, *optional*, defaults to True):
            Whether to compute the auxiliary loss for each individual sample.
        num_key_value_heads (`int`, *optional*):
            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
            `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
            by meanpooling all the original heads within that group. For more details checkout [this
            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
            `num_attention_heads`.
        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
            The non-linear activation function (function or string) in the decoder.
        max_position_embeddings (`int`, *optional*, defaults to 2048):
            The maximum sequence length that this model might ever be used with.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
            The epsilon used by the rms normalization layers.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models). Only
            relevant if `config.is_decoder=True`.
        pad_token_id (`int`, *optional*):
            Padding token id.
        bos_token_id (`int`, *optional*, defaults to 1):
            Beginning of stream token id.
        eos_token_id (`int`, *optional*, defaults to 2):
            End of stream token id.
        pretraining_tp (`int`, *optional*, defaults to 1):
            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
            document](https://huggingface.co/docs/transformers/main/perf_train_gpu_many#tensor-parallelism) to
            understand more about it. This value is necessary to ensure exact reproducibility of the pretraining
            results. Please refer to [this issue](https://github.com/pytorch/pytorch/issues/76232).
        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
            Whether to tie weight embeddings
        rope_theta (`float`, *optional*, defaults to 10000.0):
            The base period of the RoPE embeddings.
        rope_scaling (`Dict`, *optional*):
            Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
            and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
            accordingly.
            Expected contents:
                `rope_type` (`str`):
                    The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
                    'llama3'], with 'default' being the original RoPE implementation.
                `factor` (`float`, *optional*):
                    Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
                    most scaling types, a `factor` of x will enable the model to handle sequences of length x *
                    original maximum pre-trained length.
                `original_max_position_embeddings` (`int`, *optional*):
                    Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
                    pretraining.
                `attention_factor` (`float`, *optional*):
                    Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
                    computation. If unspecified, it defaults to value recommended by the implementation, using the
                    `factor` field to infer the suggested value.
                `beta_fast` (`float`, *optional*):
                    Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
                    ramp function. If unspecified, it defaults to 32.
                `beta_slow` (`float`, *optional*):
                    Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
                    ramp function. If unspecified, it defaults to 1.
                `short_factor` (`List[float]`, *optional*):
                    Only used with 'longrope'. The scaling factor to be applied to short contexts (<
                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                    size divided by the number of attention heads divided by 2
                `long_factor` (`List[float]`, *optional*):
                    Only used with 'longrope'. The scaling factor to be applied to long contexts (<
                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                    size divided by the number of attention heads divided by 2
                `low_freq_factor` (`float`, *optional*):
                    Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
                `high_freq_factor` (`float`, *optional*):
                    Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
        attention_bias (`bool`, *optional*, defaults to `False`):
            Whether to use a bias in the query, key, value and output projection layers during self-attention.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        mlp_bias (`bool`, *optional*, defaults to `False`):
            Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers.
        head_dim (`int`, *optional*):
            The attention head dimension. If None, it will default to hidden_size // num_heads

    ```python
    >>> from transformers import DeepseekModel, DeepseekConfig

    >>> configuration = DeepseekConfig()
    >>> model = DeepseekModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "deepseek"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=128256,
        hidden_size=2048,
        intermediate_size=14336,
        moe_intermediate_size = 1792,
        num_hidden_layers=28,
        num_attention_heads=16,
        num_key_value_heads=8,
        n_shared_experts = None,
        n_routed_experts = None,
        num_experts_per_tok = None,
        moe_layer_freq = 1,
        first_k_dense_replace = 0,
        norm_topk_prob = False,
        scoring_func = 'softmax',
        aux_loss_alpha = 0.001,
        seq_aux = True,
        hidden_act="silu",
        max_position_embeddings=2048,
        initializer_range=0.02,
        rms_norm_eps=1e-6,
        use_cache=True,
        pad_token_id=None,
        bos_token_id=1,
        eos_token_id=2,
        pretraining_tp=1,
        tie_word_embeddings=False,
        rope_theta=10000.0,
        rope_scaling=None,
        attention_bias=False,
        attention_dropout=0.0,
        moe_implementation="eager",
        mlp_bias=False,
        head_dim=None,
        **kwargs,
    ):
        assert moe_implementation in ('eager', ), "Invalid moe_implementation value."
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.moe_intermediate_size = moe_intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.n_shared_experts = n_shared_experts
        self.n_routed_experts = n_routed_experts
        self.num_experts_per_tok = num_experts_per_tok
        self.moe_layer_freq = moe_layer_freq
        self.first_k_dense_replace = first_k_dense_replace
        self.norm_topk_prob = norm_topk_prob
        self.scoring_func = scoring_func
        self.aux_loss_alpha = aux_loss_alpha
        self.seq_aux = seq_aux

        # for backward compatibility
        if num_key_value_heads is None:
            num_key_value_heads = num_attention_heads

        self.num_key_value_heads = num_key_value_heads
        self.hidden_act = hidden_act
        self.initializer_range = initializer_range
        self.rms_norm_eps = rms_norm_eps
        self.pretraining_tp = pretraining_tp
        self.use_cache = use_cache
        self.rope_theta = rope_theta
        self.rope_scaling = rope_scaling
        self.attention_bias = attention_bias
        self.attention_dropout = attention_dropout
        self.mlp_bias = mlp_bias
        self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads
        # Validate the correctness of rotary position embeddings parameters
        # BC: if there is a 'type' field, copy it it to 'rope_type'.
        if self.rope_scaling is not None and "type" in self.rope_scaling:
            self.rope_scaling["rope_type"] = self.rope_scaling["type"]
        rope_config_validation(self)
        self.moe_implementation = moe_implementation

        super().__init__(
            pad_token_id=pad_token_id,
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            tie_word_embeddings=tie_word_embeddings,
            **kwargs,
        )