configuration_moss.py

""" Moss model configuration"""

from transformers.utils import logging
from transformers.configuration_utils import PretrainedConfig


logger = logging.get_logger(__name__)


class MossConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`MossModel`]. It is used to instantiate a
    Moss model according to the specified arguments, defining the model architecture. 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 92494):
            Vocabulary size of the Moss model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`MossModel`]
        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 encoder.
        num_attention_heads (`int`, *optional*, defaults to 32):
            Number of attention heads for each attention layer in the Transformer encoder.
        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. Typically set this to something large
            just in case (e.g., 512 or 1024 or 2048).
        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-05):
            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`.
        tie_word_embeddings(`bool`, *optional*, defaults to `False`):
            Whether to tie weight embeddings
        Example:

    ```python
    >>> from transformers import MossModel, MossConfig

    >>> # Initializing a Moss-7b style configuration
    >>> configuration = MossConfig()

    >>> # Initializing a model from the Moss-7b style configuration
    >>> model = MossModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""
    model_type = "moss"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=92494,
        hidden_size=4096,
        intermediate_size=11008,
        num_hidden_layers=32,
        num_attention_heads=32,
        hidden_act="silu",
        max_position_embeddings=2048,
        initializer_range=0.02,
        rms_norm_eps=1e-05,
        use_cache=True,
        pad_token_id=0,
        bos_token_id=1,
        eos_token_id=2,
        tie_word_embeddings=False,
        **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
        self.hidden_act = hidden_act
        self.initializer_range = initializer_range
        self.rms_norm_eps = rms_norm_eps
        self.use_cache = use_cache
        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,
        )