DNA_bert_3 / configuration_bert.py
zhihan1996's picture
Upload 2 files
0a03898
raw
history blame
807 Bytes
# Copyright 2022 MosaicML Examples authors
# SPDX-License-Identifier: Apache-2.0
from transformers import BertConfig as TransformersBertConfig
class BertConfig(TransformersBertConfig):
def __init__(
self,
**kwargs,
):
"""Configuration class for MosaicBert.
Args:
alibi_starting_size (int): Use `alibi_starting_size` to determine how large of an alibi tensor to
create when initializing the model. You should be able to ignore this parameter in most cases.
Defaults to 512.
attention_probs_dropout_prob (float): By default, turn off attention dropout in Mosaic BERT
(otherwise, Flash Attention will be off by default). Defaults to 0.0.
"""
super().__init__(**kwargs)