Class GPT2Config

src/transformers/models/gpt2/configuration_gpt2.py:25–103

r""" summary_type (`string`, *optional*, defaults to `"cls_index"`): Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`]. Has to be one of the following options: - `"last"`: Take the last token hidden state (like XLNet).

@auto_docstring(checkpoint="openai-community/gpt2")
@strict
class GPT2Config(PreTrainedConfig):
    r"""
    summary_type (`string`, *optional*, defaults to `"cls_index"`):
        Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`].
        Has to be one of the following options:
            - `"last"`: Take the last token hidden state (like XLNet).
            - `"first"`: Take the first token hidden state (like BERT).
            - `"mean"`: Take the mean of all tokens hidden states.
            - `"cls_index"`: Supply a Tensor of classification token position (like GPT/GPT-2).
            - `"attn"`: Not implemented now, use multi-head attention.
    summary_use_proj (`bool`, *optional*, defaults to `True`):
        Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`].
        Whether or not to add a projection after the vector extraction.
    summary_activation (`str`, *optional*):
        Argument used when doing sequence summary. Used in for the multiple choice head in
        [`GPT2DoubleHeadsModel`].
        Pass `"tanh"` for a tanh activation to the output, any other value will result in no activation.
    summary_proj_to_labels (`bool`, *optional*, defaults to `True`):
        Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`].
        Whether the projection outputs should have `config.num_labels` or `config.hidden_size` classes.
    summary_first_dropout (`float`, *optional*, defaults to 0.1):
        Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`].
        The dropout ratio to be used after the projection and activation.
    scale_attn_by_inverse_layer_idx (`bool`, *optional*, defaults to `False`):
        Whether to additionally scale attention weights by `1 / layer_idx + 1`.
    reorder_and_upcast_attn (`bool`, *optional*, defaults to `False`):
        Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention
        dot-product/softmax to float() when training with mixed precision.

    Example:

    ```python
    >>> from transformers import GPT2Config, GPT2Model

    >>> # Initializing a GPT2 configuration
    >>> configuration = GPT2Config()

    >>> # Initializing a model (with random weights) from the configuration
    >>> model = GPT2Model(configuration)

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

    model_type = "gpt2"
    keys_to_ignore_at_inference = ["past_key_values"]
    attribute_map = {
        "hidden_size": "n_embd",
        "max_position_embeddings": "n_positions",
        "num_attention_heads": "n_head",
        "num_hidden_layers": "n_layer",
    }

    vocab_size: int = 50257
    n_positions: int = 1024
    n_embd: int = 768
    n_layer: int = 12
    n_head: int = 12