|
|
|
|
|
|
|
from transformers.configuration_utils import PretrainedConfig |
|
|
|
|
|
class G2PTLConfig(PretrainedConfig): |
|
r""" |
|
G2PTL model configuration |
|
|
|
Args: |
|
vocab_size (`int`, *optional*, defaults to 40000): |
|
Vocabulary size of the STELLAR model. |
|
hidden_size (`int`, *optional*, defaults to 768): |
|
Dimensionality of the encoder layers and the pooler layer. |
|
num_hidden_layers (`int`, *optional*, defaults to 12): |
|
Number of hidden layers in the Transformer encoder. |
|
num_attention_heads (`int`, *optional*, defaults to 12): |
|
Number of attention heads for each attention layer in the Transformer encoder. |
|
intermediate_size (`int`, *optional*, defaults to 3072): |
|
Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. |
|
hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`): |
|
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, |
|
`"relu"`, `"silu"` and `"gelu_new"` are supported. |
|
hidden_dropout_prob (`float`, *optional*, defaults to 0.1): |
|
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. |
|
attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): |
|
The dropout ratio for the attention probabilities. |
|
max_position_embeddings (`int`, *optional*, defaults to 512): |
|
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). |
|
type_vocab_size (`int`, *optional*, defaults to 2): |
|
The vocabulary size of the `token_type_ids` passed. |
|
task_type_vocab_size (`int`, *optional*, defaults to 3): |
|
The vocabulary size of the `task_type_ids` |
|
use_task_id (`bool`, *optional*, defaults to `False`): |
|
Whether or not the model support `task_type_ids` |
|
initializer_range (`float`, *optional*, defaults to 0.02): |
|
The standard deviation of the truncated_normal_initializer for initializing all weight matrices. |
|
layer_norm_eps (`float`, *optional*, defaults to 1e-12): |
|
The epsilon used by the layer normalization layers. |
|
position_embedding_type (`str`, *optional*, defaults to `"absolute"`): |
|
Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For |
|
positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to |
|
[Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). |
|
For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models |
|
with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658). |
|
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`. |
|
classifier_dropout (`float`, *optional*): |
|
The dropout ratio for the classification head. |
|
""" |
|
model_type = "M2PTL" |
|
|
|
def __init__( |
|
self, |
|
vocab_size=40000, |
|
hidden_size=768, |
|
num_hidden_layers=12, |
|
num_attention_heads=12, |
|
intermediate_size=3072, |
|
hidden_act="gelu", |
|
hidden_dropout_prob=0.1, |
|
attention_probs_dropout_prob=0.1, |
|
max_position_embeddings=2048, |
|
type_vocab_size=4, |
|
task_type_vocab_size=3, |
|
use_task_id=True, |
|
initializer_range=0.02, |
|
layer_norm_eps=1e-05, |
|
pad_token_id=0, |
|
position_embedding_type="absolute", |
|
use_cache=True, |
|
classifier_dropout=None, |
|
**kwargs |
|
): |
|
super().__init__(pad_token_id=pad_token_id, **kwargs) |
|
|
|
self.vocab_size = vocab_size |
|
self.hidden_size = hidden_size |
|
self.num_hidden_layers = num_hidden_layers |
|
self.num_attention_heads = num_attention_heads |
|
self.hidden_act = hidden_act |
|
self.intermediate_size = intermediate_size |
|
self.hidden_dropout_prob = hidden_dropout_prob |
|
self.attention_probs_dropout_prob = attention_probs_dropout_prob |
|
self.max_position_embeddings = max_position_embeddings |
|
self.type_vocab_size = type_vocab_size |
|
self.task_type_vocab_size = task_type_vocab_size |
|
self.use_task_id = use_task_id |
|
self.initializer_range = initializer_range |
|
self.layer_norm_eps = layer_norm_eps |
|
self.position_embedding_type = position_embedding_type |
|
self.use_cache = use_cache |
|
self.classifier_dropout = classifier_dropout |
|
|
|
|
