configuration_exaone.py

# coding=utf-8
# Copyright 2021 The LG AI Research EXAONE Lab. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""EXAONE model configuration"""

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


logger = logging.get_logger(__name__)

EXAONE_PRETRAINED_CONFIG_ARCHIVE_MAP = {}


class ExaoneConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`ExaoneModel`]. It is used to
    instantiate a EXAONE 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 EXAONE-3.0-7.8B-Instruct [LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct)

    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 102400):
            Vocabulary size of the EXAONE model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`ExaoneModel`]. Vocabulary size of the model.
            Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of
            [`ExaoneModel`].
        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).
        hidden_size (`int`, *optional*, defaults to 2048):
            Dimensionality of the encoder layers and the pooler layer.
        num_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 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 checkout [this
            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
            `num_attention_heads`.
        intermediate_size (`int`, *optional*, defaults to `hidden_size * 4`):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        activation_function (`str` or `function`, *optional*, defaults to `"silu"`):
            The non-linear activation function (function or string) in the decoder.
        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
        embed_dropout (`float`, *optional*, defaults to 0.0):
            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        layer_norm_epsilon (`float`, *optional*, defaults to 1e-05):
            The epsilon used by the layer normalization layers.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        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``.
        bos_token_id (`int`, *optional*, defaults to 0):
            Beginning of stream token id.
        eos_token_id (`int`, *optional*, defaults to 2):
            End of stream token id.

    Example:

    ```python
    >>> from transformers import EXAONEModel, ExaoneConfig

    >>> # Initializing a EXAONE configuration
    >>> configuration = ExaoneConfig()

    >>> # Initializing a model from configuration
    >>> model = EXAONEModel(configuration)

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

    model_type = "exaone"
    keys_to_ignore_at_inference = ["past_key_values"]
    attribute_map = {"num_hidden_layers": "num_layers"}

    def __init__(
        self,
        vocab_size=102400,
        max_position_embeddings=2048,
        hidden_size=2048,
        num_layers=32,
        num_attention_heads=32,
        num_key_value_heads=None,
        intermediate_size=None,
        activation_function="silu",
        rope_theta=10000.0,
        rope_scaling=None,
        embed_dropout=0.0,
        attention_dropout=0.0,
        layer_norm_epsilon=1e-5,
        initializer_range=0.02,
        use_cache=True,
        bos_token_id=0,
        eos_token_id=2,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.num_attention_heads = num_attention_heads
        self.num_layers = num_layers
        if num_key_value_heads is None:
            num_key_value_heads = num_attention_heads
        self.num_key_value_heads = num_key_value_heads
        if intermediate_size:
            self.intermediate_size = intermediate_size
        else:
            self.intermediate_size = hidden_size * 4
        self.activation_function = activation_function
        self.embed_dropout = embed_dropout
        self.attention_dropout = attention_dropout
        self.layer_norm_epsilon = layer_norm_epsilon
        self.initializer_range = initializer_range
        self.use_cache = use_cache
        self.rope_theta = rope_theta
        self.rope_scaling = rope_scaling

        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id

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