transformers/examples/modular-transformers/configuration_my_new_model.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from examples/modular-transformers/modular_my_new_model.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_my_new_model.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨

from huggingface_hub.dataclasses import strict

from ...configuration_utils import PreTrainedConfig
from ...modeling_rope_utils import RopeParameters
from ...utils import auto_docstring
from ...utils.type_validators import interval


@auto_docstring(checkpoint="meta-my_new_model/MyNewModel-2-7b-hf")
@strict
class MyNewModelConfig(PreTrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`MyNewModelModel`]. It is used to instantiate an MyNewModel
    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 MyNewModel-7B.
    e.g. [meta-my_new_model/MyNewModel-2-7b-hf](https://huggingface.co/meta-my_new_model/MyNewModel-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 MyNewModel model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`MyNewModelModel`]
        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. MyNewModel 1 supports up to 2048 tokens,
            MyNewModel 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_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',
                    'my_new_model3'], 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 'my_new_model3'. 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 'my_new_model3'. Scaling factor applied to low frequency components of the RoPE
                `high_freq_factor` (`float`, *optional*):
                    Only used with 'my_new_model3'. 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_attention_heads

    ```python
    >>> from transformers import MyNewModelModel, MyNewModelConfig

    >>> # Initializing a MyNewModel my_new_model-7b style configuration
    >>> configuration = MyNewModelConfig()

    >>> # Initializing a model from the my_new_model-7b style configuration
    >>> model = MyNewModelModel(configuration)

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

    model_type = "my_new_model"
    keys_to_ignore_at_inference = ["past_key_values"]
    # Default tensor parallel plan for base model `MyNewModelModel`
    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"]),
    }

    vocab_size: int = 32000
    hidden_size: int = 4096
    intermediate_size: int = 11008
    num_hidden_layers: int = 32
    num_attention_heads: int = 32
    num_key_value_heads: int | None = None
    hidden_act: str = "silu"
    max_position_embeddings: int = 2048
    initializer_range: float = interval(min=0.0, max=1.0)(default=0.02)
    rms_norm_eps: float = 1e-6
    use_cache: bool = True
    pad_token_id: int | None = None
    bos_token_id: int | None = 1
    eos_token_id: int | list[int] | None = 2
    pretraining_tp: int | None = 1
    tie_word_embeddings: bool = False
    rope_parameters: RopeParameters | dict | None = None
    attention_bias: bool = False
    attention_dropout: int | float | None = 0.0

    mlp_bias: bool = True
    head_dim: int | None = None
    new_param: int = 0

    def __post_init__(self, **kwargs):
        if self.head_dim is None:
            self.head_dim = self.hidden_size // self.num_attention_heads
        if self.num_key_value_heads is None:
            self.num_key_value_heads = self.num_attention_heads

        super().__post_init__(**kwargs)

    def validate_architecture(self):
        """Part of `@strict`-powered validation. Validates the architecture of the config."""
        if self.hidden_size % self.num_attention_heads != 0:
            raise ValueError(
                f"The hidden size ({self.hidden_size}) is not a multiple of the number of attention "
                f"heads ({self.num_attention_heads})."
            )