Spaces:
Sleeping
Sleeping
File size: 3,537 Bytes
2260825 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
# Copyright 2020 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import math
import torch
from packaging import version
from torch import nn
from .utils import logging
logger = logging.get_logger(__name__)
def _gelu_python(x):
"""
Original Implementation of the GELU activation function in Google BERT repo when initially created. For
information: OpenAI GPT's GELU is slightly different (and gives slightly different results): 0.5 * x * (1 +
torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3)))) This is now written in C in nn.functional
Also see the Gaussian Error Linear Units paper: https://arxiv.org/abs/1606.08415
"""
return x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0)))
def gelu_new(x):
"""
Implementation of the GELU activation function currently in Google BERT repo (identical to OpenAI GPT). Also see
the Gaussian Error Linear Units paper: https://arxiv.org/abs/1606.08415
"""
return 0.5 * x * (1.0 + torch.tanh(math.sqrt(2.0 / math.pi) * (x + 0.044715 * torch.pow(x, 3.0))))
if version.parse(torch.__version__) < version.parse("1.4"):
gelu = _gelu_python
else:
gelu = nn.functional.gelu
def gelu_fast(x):
return 0.5 * x * (1.0 + torch.tanh(x * 0.7978845608 * (1.0 + 0.044715 * x * x)))
def quick_gelu(x):
return x * torch.sigmoid(1.702 * x)
def _silu_python(x):
"""
See Gaussian Error Linear Units (Hendrycks et al., https://arxiv.org/abs/1606.08415) where the SiLU (Sigmoid Linear
Unit) was originally introduced and coined, and see Sigmoid-Weighted Linear Units for Neural Network Function
Approximation in Reinforcement Learning (Elfwing et al., https://arxiv.org/abs/1702.03118) and Swish: a Self-Gated
Activation Function (Ramachandran et al., https://arxiv.org/abs/1710.05941v1) where the SiLU was experimented with
later.
"""
return x * torch.sigmoid(x)
if version.parse(torch.__version__) < version.parse("1.7"):
silu = _silu_python
else:
silu = nn.functional.silu
def _mish_python(x):
"""
See Mish: A Self-Regularized Non-Monotonic Activation Function (Misra., https://arxiv.org/abs/1908.08681). Also
visit the official repository for the paper: https://github.com/digantamisra98/Mish
"""
return x * torch.tanh(nn.functional.softplus(x))
if version.parse(torch.__version__) < version.parse("1.9"):
mish = _mish_python
else:
mish = nn.functional.mish
def linear_act(x):
return x
ACT2FN = {
"relu": nn.functional.relu,
"silu": silu,
"swish": silu,
"gelu": gelu,
"tanh": torch.tanh,
"gelu_new": gelu_new,
"gelu_fast": gelu_fast,
"quick_gelu": quick_gelu,
"mish": mish,
"linear": linear_act,
"sigmoid": torch.sigmoid,
}
def get_activation(activation_string):
if activation_string in ACT2FN:
return ACT2FN[activation_string]
else:
raise KeyError(f"function {activation_string} not found in ACT2FN mapping {list(ACT2FN.keys())}")
|