examples/modular-transformers/configuration_duplicated_method.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from examples/modular-transformers/modular_duplicated_method.py.
#               Do NOT edit this file manually as any edits will be overwritten by the generation of
#             the file from the modular. If any change should be done, please apply the change to the
#                          modular_duplicated_method.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨

from ...configuration_utils import PreTrainedConfig
from ...modeling_rope_utils import RopeParameters


class DuplicatedMethodConfig(PreTrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`DuplicatedMethodModel`]. It is used to instantiate an DuplicatedMethod
    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 DuplicatedMethod-7B.
    e.g. [meta-duplicated_method/DuplicatedMethod-2-7b-hf](https://huggingface.co/meta-duplicated_method/DuplicatedMethod-2-7b-hf)

    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 32000):
            Vocabulary size of the DuplicatedMethod model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`DuplicatedMethodModel`]
        hidden_size (`int`, *optional*, defaults to 4096):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 11008):
            Dimension of the MLP 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.
        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, check out [this
            paper](https://huggingface.co/papers/2305.13245). 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. DuplicatedMethod 1 supports up to 2048 tokens,
            DuplicatedMethod 2 up to 4096, CodeLlama up to 16384.
        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_parameters (`RopeParameters`, *optional*):
            Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain
            a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE
            with longer `max_position_embeddings`.
        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_attention_heads

    ```python
    >>> from transformers import DuplicatedMethodModel, DuplicatedMethodConfig

    >>> # Initializing a DuplicatedMethod duplicated_method-7b style configuration
    >>> configuration = DuplicatedMethodConfig()

    >>> # Initializing a model from the duplicated_method-7b style configuration
    >>> model = DuplicatedMethodModel(configuration)

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

    model_type = "duplicated_method"
    keys_to_ignore_at_inference = ["past_key_values"]
    # Default tensor parallel plan for base model `DuplicatedMethodModel`
    base_model_tp_plan = {
        "layers.*.self_attn.q_proj": "colwise",
        "layers.*.self_attn.k_proj": "colwise",
        "layers.*.self_attn.v_proj": "colwise",
        "layers.*.self_attn.o_proj": "rowwise",
        "layers.*.mlp.gate_proj": "colwise",
        "layers.*.mlp.up_proj": "colwise",
        "layers.*.mlp.down_proj": "rowwise",
    }
    base_model_pp_plan = {
        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
        "norm": (["hidden_states"], ["hidden_states"]),
    }

    def __init__(
        self,
        vocab_size: int | None = 32000,
        hidden_size: int | None = 4096,
        intermediate_size: int | None = 11008,
        num_hidden_layers: int | None = 32,
        num_attention_heads: int | None = 32,
        num_key_value_heads: int | None = None,
        hidden_act: str | None = "silu",
        max_position_embeddings: int | None = 2048,
        initializer_range: float | None = 0.02,
        rms_norm_eps: int | None = 1e-6,
        use_cache: bool | None = True,
        pad_token_id: int | None = None,
        bos_token_id: int | None = 1,
        eos_token_id: int | None = 2,
        pretraining_tp: int | None = 1,
        tie_word_embeddings: bool | None = False,
        rope_parameters: RopeParameters | dict[str, RopeParameters] | None = None,
        attention_bias: bool | None = False,
        attention_dropout: float | None = 0.0,
        mlp_bias: bool | None = False,
        head_dim: int | None = None,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads

        # 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.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
        self.rope_parameters = rope_parameters

        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,
        )

    @property
    def vocab_size(self):
        return 45

    @vocab_size.setter
    def vocab_size(self, value):
        self.vocab_size = value