tj d Z ddlmZ ddlmZ ddlmZmZ ej e Z
ed e G d d e Z d gZ d
S ) zXLNet configuration )strict )PreTrainedConfig)auto_docstringloggingzxlnet/xlnet-large-cased)
checkpointc B e Zd ZU dZdZdgZdddddZd Zee d< d
Z
ee d< d Z ee d< d Z ee d< d
Z
ee d< dZedz e d< dZee d< dZee d< dZee d< dZee d< dZeez e d< dZedz e d < dZedz e d < d Zee d < d Zee d!< d Zee d"< d#Z ee d$< d Z ee d%< d&Z ee d'< d Z ee d(< d)Z ee d*< dZ!eez e d+< d,Z"ee d-< d,Z#ee d.< d,Z$edz e d/< d0Z%edz e d1< d2Z&ee'e z dz e d3< d Z(ee d4< fd5Z)d6 Z*e+d7 Z,e,j- d8 Z, xZ.S )9 XLNetConfiga
ff_activation (`str` or `Callable`, *optional*, defaults to `"gelu"`):
The non-linear activation function (function or string) in the If string, `"gelu"`, `"relu"`, `"silu"` and
`"gelu_new"` are supported.
attn_type (`str`, *optional*, defaults to `"bi"`):
The attention type used by the model. Set `"bi"` for XLNet, `"uni"` for Transformer-XL.
mem_len (`int` or `None`, *optional*):
The number of tokens to cache. The key/value pairs that have already been pre-computed in a previous
forward pass won't be re-computed. See the
[quickstart](https://huggingface.co/transformers/quickstart.html#using-the-past) for more information.
reuse_len (`int`, *optional*):
The number of tokens in the current batch to be cached and reused in the future.
use_mems_eval (`bool`, *optional*, defaults to `True`):
Whether or not the model should make use of the recurrent memory mechanism in evaluation mode.
use_mems_train (`bool`, *optional*, defaults to `False`):
Whether or not the model should make use of the recurrent memory mechanism in train mode.
For pretraining, it is recommended to set `use_mems_train` to `True`. For fine-tuning, it is recommended to
set `use_mems_train` to `False` as discussed
[here](https://github.com/zihangdai/xlnet/issues/41#issuecomment-505102587). If `use_mems_train` is set to
`True`, one has to make sure that the train batches are correctly pre-processed, *e.g.* `batch_1 = [[This
line is], [This is the]]` and `batch_2 = [[ the first line], [ second line]]` and that all batches are of
equal size.
bi_data (`bool`, *optional*, defaults to `False`):
Whether or not to use bidirectional input pipeline. Usually set to `True` during pretraining and `False`
during finetuning.
clamp_len (`int`, *optional*, defaults to -1):
Clamp all relative distances larger than clamp_len. Setting this attribute to -1 means no clamping.
same_length (`bool`, *optional*, defaults to `False`):
Whether or not to use the same attention length for each token.
summary_type (`str`, *optional*, defaults to "last"):
Argument used when doing sequence summary. Used in the sequence classification and multiple choice models.
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 sequence classification and multiple choice models.
Whether or not to add a projection after the vector extraction.
summary_activation (`str`, *optional*):
Argument used when doing sequence summary. Used in the sequence classification and multiple choice models.
Pass `"tanh"` for a tanh activation to the output, any other value will result in no activation.
summary_last_dropout (`float`, *optional*, defaults to 0.1):
Used in the sequence classification and multiple choice models.
The dropout ratio to be used after the projection and activation.
start_n_top (`int`, *optional*, defaults to 5):
Used in the SQuAD evaluation script.
end_n_top (`int`, *optional*, defaults to 5):
Used in the SQuAD evaluation script.
Examples:
```python
>>> from transformers import XLNetConfig, XLNetModel
>>> # Initializing a XLNet configuration
>>> configuration = XLNetConfig()
>>> # Initializing a model (with random weights) from the configuration
>>> model = XLNetModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```xlnetmems
vocab_sized_modeln_headn_layer)n_token hidden_sizenum_attention_headsnum_hidden_layersi } i i d_innerNd_headgelu
ff_activationbi attn_typeg{Gz?initializer_rangeg-q=layer_norm_epsg?dropouti mem_len reuse_lenT
use_mems_evalFuse_mems_trainbi_data clamp_len same_lengthlast summary_typesummary_use_projtanhsummary_activationsummary_last_dropout start_n_top end_n_top pad_token_id bos_token_id eos_token_idtie_word_embeddingsc p | j p| j | j z | _ t j di | d S )N )r r r super
__post_init__)selfkwargs __class__s k/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/xlnet/configuration_xlnet.pyr: zXLNetConfig.__post_init__ s= k@T\T[%@ ''''''' c | j | j z dk r t d| j | j z d | j | j | j z k r(t d| j d| j | j z d dS )zOPart of `@strict`-powered validation. Validates the architecture of the config.r z'd_model % n_head' (z) should be equal to 0z
`d_head` (z*) should be equal to `d_model // n_head` ()N)r r
ValueErrorr r; s r> validate_architecturez!XLNetConfig.validate_architecture s <$+ % * * fDL4;4N f f fgg g ;$,$+5 5 5 rT[rrTXT`dhdoTorrr
6 5r? c L t d| j d dS )N
The model < is one of the few models that has no sequence length limit.r% )loggerinfo
model_typerC s r> max_position_embeddingsz#XLNetConfig.max_position_embeddings s' n nnnooorr? c 2 t d| j d )NrF rG )NotImplementedErrorrJ )r; values r> rK z#XLNetConfig.max_position_embeddings s& " f f f f
r? )/__name__
__module__ __qualname____doc__rJ keys_to_ignore_at_inference
attribute_mapr
int__annotations__r r r r r r strr r floatr r r r! r" boolr# r$ r& r' r) r* r, r- r/ r0 r1 r3 r5 listr6 r: rD propertyrK setter
__classcell__)r= s @r> r
r
s B B H J#)( ' & M JGSGSFCGS FC$J M3 Is #u### !NE!!! GUS[ GS4Z IsTz M4 ND GTIs K L# !d!!! $$$$(+%#++++KIs L#* L#* +,L#S /D(,,, $$$$( ( ( ( ( X #
$#
r? r
N)
rR huggingface_hub.dataclassesr configuration_utilsr utilsr r
get_loggerrO rH r
__all__r8 r? r> rc s . . . . . . 3 3 3 3 3 3 , , , , , , , ,
H % % 4555B
B
B
B
B
" B
B
65B
J /r?