wehub-resource-sync
48 lines
1.4 KiB
Python
48 lines
1.4 KiB
Python
from transformers.configuration_utils import PretrainedConfig
|
|
|
|
from surya.common.s3 import S3DownloaderMixin
|
|
|
|
ID2LABEL = {0: "good", 1: "bad"}
|
|
|
|
|
|
class DistilBertConfig(S3DownloaderMixin, PretrainedConfig):
|
|
model_type = "distilbert"
|
|
attribute_map = {
|
|
"hidden_size": "dim",
|
|
"num_attention_heads": "n_heads",
|
|
"num_hidden_layers": "n_layers",
|
|
}
|
|
|
|
def __init__(
|
|
self,
|
|
vocab_size=30522,
|
|
max_position_embeddings=512,
|
|
sinusoidal_pos_embds=False,
|
|
n_layers=6,
|
|
n_heads=12,
|
|
dim=768,
|
|
hidden_dim=4 * 768,
|
|
dropout=0.1,
|
|
attention_dropout=0.1,
|
|
activation="gelu",
|
|
initializer_range=0.02,
|
|
qa_dropout=0.1,
|
|
seq_classif_dropout=0.2,
|
|
pad_token_id=0,
|
|
**kwargs,
|
|
):
|
|
self.vocab_size = vocab_size
|
|
self.max_position_embeddings = max_position_embeddings
|
|
self.sinusoidal_pos_embds = sinusoidal_pos_embds
|
|
self.n_layers = n_layers
|
|
self.n_heads = n_heads
|
|
self.dim = dim
|
|
self.hidden_dim = hidden_dim
|
|
self.dropout = dropout
|
|
self.attention_dropout = attention_dropout
|
|
self.activation = activation
|
|
self.initializer_range = initializer_range
|
|
self.qa_dropout = qa_dropout
|
|
self.seq_classif_dropout = seq_classif_dropout
|
|
super().__init__(**kwargs, pad_token_id=pad_token_id)
|