# Copyright © 2022 BAAI. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License")
# coding=utf-8
# Copyright (c) 2019, NVIDIA CORPORATION.  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 torch
import math


@torch.jit.script
def gelu_impl(x):
    """OpenAI's gelu implementation."""
    return 0.5 * x * (1.0 + torch.tanh(0.7978845608028654 * x *
                                       (1.0 + 0.044715 * x * x)))


def gelu(x):
    return gelu_impl(x)


def unscaled_init_method(sigma):
    """Init method based on N(0, sigma)."""

    def init_(tensor):
        return torch.nn.init.normal_(tensor, mean=0.0, std=sigma)

    return init_


def scaled_init_method(sigma, num_layers):
    """Init method based on N(0, sigma/sqrt(2*num_layers)."""
    std = sigma / math.sqrt(2.0 * num_layers)

    def init_(tensor):
        return torch.nn.init.normal_(tensor, mean=0.0, std=std)

    return init_


def sqrt(x):
    return int(math.sqrt(x) + 1e-4)