// author: hotman78
// date: 2024/04/20-12:32:36

// --- begin raw code -----------------
// #include"cpplib/util/template.hpp"
// // #include"cpplib/graph_tree/dijkstra.hpp"
// #include"cpplib/math/ACL_modint998244353.hpp"
// #include"cpplib/math/lagrange_interpolation.hpp"
// 
// void solve(){
//     lint n,k;
//     cin>>n>>k;
//     vector<mint>v1(k+3,0),v2(k+3,0);
//     rep(i,1,k+3){
//         v1[i]=v1[i-1]+mint(i).pow(k);
//         v2[i]=v2[i-1]+mint(i).pow(k+1);
//     }
//     mint ans=lagrange_interpolation<mint>(v1,n)*n-lagrange_interpolation<mint>(v2,n);
//     vector<mint>tb={1, 945896249,826994544,147972654,718271290,311054462,848172652,487479281,181218541,225032295,464016596,303879624,711595889,801978400,274311861,262505243,197661226,560969645,59654808,844084429,63299249,656698209,745706197,782663844,722450722,437503635,974490943,756414660,100919583,567153381,434731971,992060846,397327632,588176542,152285902,561146832,410851918,739984378,631617451,918814530,55395755,984167498,880949811,904643816,713793642,44666331,712775427,443688906,488198727,374504494,15814281,809754637,581403016,931134979,415434801,733417940,522329741,396654552,691138193,924037483,565294571,647279052,93888746,491863506,860288574,933267285,420593226,601485588,643768503,139726730,293833759,963402916,983736712,496456348,270369543,205793557,946545391,54554286,827540230,533325452,851627080,695240733,872441336,641905269,107293455,814887934,659546511,435069442,36312125,691840784,130777589,586041601,696055209,627965301,914253051,159075500,818001905,839514995,613224734,923597279,0};
//     ans*=tb[n/10000000];
//     rep(i,1,n%10000000){
//         ans*=n/10000000*10000000+i;
//     }
//     ans*=2;
//     cout<<ans<<endl;
// }
// 
// int main(){
//     // mint t=1;
//     // rep(i,1,1000000001){
//     //     if(i%10000000==0)cout<<t<<",";
//     //     t*=i;
//     // }
// 
//     solve();
//     // lint t;cin>>t;while(t--)solve();
// }
// --- end raw code -----------------

#line 2 "cpplib/util/template.hpp"
#ifdef LOCAL
#define _GLIBCXX_DEBUG
#endif
#pragma GCC optimize("Ofast")
#pragma GCC optimize("unroll-loops")
// #pragma GCC target("avx2")
#include <bits/stdc++.h>
using namespace std;
#line 1 "cpplib/util/ioutil.hpp"
// template <class Head,class... Args>
// std::ostream& output(std::ostream& out,const Head& head,const Args&... args){
//     out>>head;
//     return output(head,args...);
// }
// template <class Head>
// std::ostream& output(std::ostream& out,const Head& head){
//     out>>head;
//     return out;
// }

template <typename T, typename E>
std::ostream &operator<<(std::ostream &out, std::pair<T, E> v) {
    out << "(" << v.first << "," << v.second << ")";
    return out;
}

// template <class... Args>
// ostream& operator<<(ostream& out,std::tuple<Args...>v){
//     std::apply(output,v);
//     return out;
// }
#line 11 "cpplib/util/template.hpp"
struct __INIT__ {
    __INIT__() {
        cin.tie(0);
        ios::sync_with_stdio(false);
        cout << fixed << setprecision(15);
    }
} __INIT__;
typedef long long lint;
constexpr long long INF = 1LL << 60;
constexpr int IINF = 1 << 30;
constexpr double EPS = 1e-10;
#ifndef REACTIVE
#define endl '\n';
#endif
typedef vector<lint> vec;
typedef vector<vector<lint>> mat;
typedef vector<vector<vector<lint>>> mat3;
typedef vector<string> svec;
typedef vector<vector<string>> smat;
template <typename T> using V = vector<T>;
template <typename T> using VV = V<V<T>>;
#define output(t)                                                              \
    {                                                                          \
        bool f = 0;                                                            \
        for (auto val : (t)) {                                                 \
            cout << (f ? " " : "") << val;                                     \
            f = 1;                                                             \
        }                                                                      \
        cout << endl;                                                          \
    }
#define output2(t)                                                             \
    {                                                                          \
        for (auto i : t)                                                       \
            output(i);                                                         \
    }
#define debug(t)                                                               \
    {                                                                          \
        bool f = 0;                                                            \
        for (auto i : t) {                                                     \
            cerr << (f ? " " : "") << i;                                       \
            f = 1;                                                             \
        }                                                                      \
        cerr << endl;                                                          \
    }
#define debug2(t)                                                              \
    {                                                                          \
        for (auto i : t)                                                       \
            debug(i);                                                          \
    }
#define loop(n) for (long long _ = 0; _ < (long long)(n); ++_)
#define _overload4(_1, _2, _3, _4, name, ...) name
#define __rep(i, a) repi(i, 0, a, 1)
#define _rep(i, a, b) repi(i, a, b, 1)
#define repi(i, a, b, c)                                                       \
    for (long long i = (long long)(a); i < (long long)(b); i += c)
#define rep(...) _overload4(__VA_ARGS__, repi, _rep, __rep)(__VA_ARGS__)
#define _overload3_rev(_1, _2, _3, name, ...) name
#define _rep_rev(i, a) repi_rev(i, 0, a)
#define repi_rev(i, a, b)                                                      \
    for (long long i = (long long)(b)-1; i >= (long long)(a); --i)
#define rrep(...) _overload3_rev(__VA_ARGS__, repi_rev, _rep_rev)(__VA_ARGS__)

#define all(n) begin(n), end(n)
template <typename T, typename E> bool chmin(T &s, const E &t) {
    bool res = s > t;
    s = min<T>(s, t);
    return res;
}
template <typename T, typename E> bool chmax(T &s, const E &t) {
    bool res = s < t;
    s = max<T>(s, t);
    return res;
}
const vector<lint> dx = {1, 0, -1, 0, 1, 1, -1, -1};
const vector<lint> dy = {0, 1, 0, -1, 1, -1, 1, -1};
#define SUM(v) accumulate(all(v), 0LL)
#if __cplusplus >= 201703L
template <typename T, typename... Args>
auto make_vector(T x, int arg, Args... args) {
    if constexpr (sizeof...(args) == 0)
        return vector<T>(arg, x);
    else
        return vector(arg, make_vector<T>(x, args...));
}
#endif
#define bit(n, a) ((n >> a) & 1)
#define extrep(v, ...) for (auto v : make_mat_impl({__VA_ARGS__}))
vector<vector<long long>> make_mat_impl(vector<long long> v) {
    if (v.empty())
        return vector<vector<long long>>(1, vector<long long>());
    long long n = v.back();
    v.pop_back();
    vector<vector<long long>> ret;
    vector<vector<long long>> tmp = make_mat_impl(v);
    for (auto e : tmp)
        for (long long i = 0; i < n; ++i) {
            ret.push_back(e);
            ret.back().push_back(i);
        }
    return ret;
}
using graph = vector<vector<int>>;
template <typename T> using graph_w = vector<vector<pair<int, T>>>;

#if __cplusplus >= 201703L
constexpr inline long long powll(long long a, long long b) {
    long long res = 1;
    while (b--)
        res *= a;
    return res;
}
#endif

template <typename T, typename E>
pair<T, E> &operator+=(pair<T, E> &s, const pair<T, E> &t) {
    s.first += t.first;
    s.second += t.second;
    return s;
}
template <typename T, typename E>
pair<T, E> &operator-=(pair<T, E> &s, const pair<T, E> &t) {
    s.first -= t.first;
    s.second -= t.second;
    return s;
}
template <typename T, typename E>
pair<T, E> operator+(const pair<T, E> &s, const pair<T, E> &t) {
    auto res = s;
    return res += t;
}
template <typename T, typename E>
pair<T, E> operator-(const pair<T, E> &s, const pair<T, E> &t) {
    auto res = s;
    return res -= t;
}
#define BEGIN_STACK_EXTEND(size)                                               \
    void *stack_extend_memory_ = malloc(size);                                 \
    void *stack_extend_origin_memory_;                                         \
    char *stack_extend_dummy_memory_ = (char *)alloca(                         \
        (1 + (int)(((long long)stack_extend_memory_) & 127)) * 16);            \
    *stack_extend_dummy_memory_ = 0;                                           \
    asm volatile("mov %%rsp, %%rbx\nmov %%rax, %%rsp"                          \
                 : "=b"(stack_extend_origin_memory_)                           \
                 : "a"((char *)stack_extend_memory_ + (size)-1024));
#define END_STACK_EXTEND                                                       \
    asm volatile("mov %%rax, %%rsp" ::"a"(stack_extend_origin_memory_));       \
    free(stack_extend_memory_);
int floor_pow(int n) { return n ? 31 - __builtin_clz(n) : 0; }
#line 2 "main.cpp"
// #include"cpplib/graph_tree/dijkstra.hpp"
#line 2 "cpplib/math/ACL_modint998244353.hpp"

#include <cassert>
#include <numeric>
#include <type_traits>

#ifdef _MSC_VER
#include <intrin.h>
#endif

#include <utility>

#ifdef _MSC_VER
#include <intrin.h>
#endif

namespace atcoder {

namespace internal {

constexpr long long safe_mod(long long x, long long m) {
    x %= m;
    if (x < 0)
        x += m;
    return x;
}

struct barrett {
    unsigned int _m;
    unsigned long long im;

    explicit barrett(unsigned int m)
        : _m(m), im((unsigned long long)(-1) / m + 1) {}

    unsigned int umod() const { return _m; }

    unsigned int mul(unsigned int a, unsigned int b) const {

        unsigned long long z = a;
        z *= b;
#ifdef _MSC_VER
        unsigned long long x;
        _umul128(z, im, &x);
#else
        unsigned long long x =
            (unsigned long long)(((unsigned __int128)(z)*im) >> 64);
#endif
        unsigned int v = (unsigned int)(z - x * _m);
        if (_m <= v)
            v += _m;
        return v;
    }
};

constexpr long long pow_mod_constexpr(long long x, long long n, int m) {
    if (m == 1)
        return 0;
    unsigned int _m = (unsigned int)(m);
    unsigned long long r = 1;
    unsigned long long y = safe_mod(x, m);
    while (n) {
        if (n & 1)
            r = (r * y) % _m;
        y = (y * y) % _m;
        n >>= 1;
    }
    return r;
}

constexpr bool is_prime_constexpr(int n) {
    if (n <= 1)
        return false;
    if (n == 2 || n == 7 || n == 61)
        return true;
    if (n % 2 == 0)
        return false;
    long long d = n - 1;
    while (d % 2 == 0)
        d /= 2;
    constexpr long long bases[3] = {2, 7, 61};
    for (long long a : bases) {
        long long t = d;
        long long y = pow_mod_constexpr(a, t, n);
        while (t != n - 1 && y != 1 && y != n - 1) {
            y = y * y % n;
            t <<= 1;
        }
        if (y != n - 1 && t % 2 == 0) {
            return false;
        }
    }
    return true;
}
template <int n> constexpr bool is_prime = is_prime_constexpr(n);

constexpr std::pair<long long, long long> inv_gcd(long long a, long long b) {
    a = safe_mod(a, b);
    if (a == 0)
        return {b, 0};

    long long s = b, t = a;
    long long m0 = 0, m1 = 1;

    while (t) {
        long long u = s / t;
        s -= t * u;
        m0 -= m1 * u; // |m1 * u| <= |m1| * s <= b

        auto tmp = s;
        s = t;
        t = tmp;
        tmp = m0;
        m0 = m1;
        m1 = tmp;
    }
    if (m0 < 0)
        m0 += b / s;
    return {s, m0};
}

constexpr int primitive_root_constexpr(int m) {
    if (m == 2)
        return 1;
    if (m == 167772161)
        return 3;
    if (m == 469762049)
        return 3;
    if (m == 754974721)
        return 11;
    if (m == 998244353)
        return 3;
    int divs[20] = {};
    divs[0] = 2;
    int cnt = 1;
    int x = (m - 1) / 2;
    while (x % 2 == 0)
        x /= 2;
    for (int i = 3; (long long)(i)*i <= x; i += 2) {
        if (x % i == 0) {
            divs[cnt++] = i;
            while (x % i == 0) {
                x /= i;
            }
        }
    }
    if (x > 1) {
        divs[cnt++] = x;
    }
    for (int g = 2;; g++) {
        bool ok = true;
        for (int i = 0; i < cnt; i++) {
            if (pow_mod_constexpr(g, (m - 1) / divs[i], m) == 1) {
                ok = false;
                break;
            }
        }
        if (ok)
            return g;
    }
}
template <int m> constexpr int primitive_root = primitive_root_constexpr(m);

unsigned long long floor_sum_unsigned(unsigned long long n,
                                      unsigned long long m,
                                      unsigned long long a,
                                      unsigned long long b) {
    unsigned long long ans = 0;
    while (true) {
        if (a >= m) {
            ans += n * (n - 1) / 2 * (a / m);
            a %= m;
        }
        if (b >= m) {
            ans += n * (b / m);
            b %= m;
        }

        unsigned long long y_max = a * n + b;
        if (y_max < m)
            break;
        n = (unsigned long long)(y_max / m);
        b = (unsigned long long)(y_max % m);
        std::swap(m, a);
    }
    return ans;
}

} // namespace internal

} // namespace atcoder

#include <cassert>
#include <numeric>
#include <type_traits>

namespace atcoder {

namespace internal {

#ifndef _MSC_VER
template <class T>
using is_signed_int128 =
    typename std::conditional<std::is_same<T, __int128_t>::value ||
                                  std::is_same<T, __int128>::value,
                              std::true_type, std::false_type>::type;

template <class T>
using is_unsigned_int128 =
    typename std::conditional<std::is_same<T, __uint128_t>::value ||
                                  std::is_same<T, unsigned __int128>::value,
                              std::true_type, std::false_type>::type;

template <class T>
using make_unsigned_int128 =
    typename std::conditional<std::is_same<T, __int128_t>::value, __uint128_t,
                              unsigned __int128>;

template <class T>
using is_integral =
    typename std::conditional<std::is_integral<T>::value ||
                                  is_signed_int128<T>::value ||
                                  is_unsigned_int128<T>::value,
                              std::true_type, std::false_type>::type;

template <class T>
using is_signed_int =
    typename std::conditional<(is_integral<T>::value &&
                               std::is_signed<T>::value) ||
                                  is_signed_int128<T>::value,
                              std::true_type, std::false_type>::type;

template <class T>
using is_unsigned_int =
    typename std::conditional<(is_integral<T>::value &&
                               std::is_unsigned<T>::value) ||
                                  is_unsigned_int128<T>::value,
                              std::true_type, std::false_type>::type;

template <class T>
using to_unsigned = typename std::conditional<
    is_signed_int128<T>::value, make_unsigned_int128<T>,
    typename std::conditional<std::is_signed<T>::value, std::make_unsigned<T>,
                              std::common_type<T>>::type>::type;

#else

template <class T> using is_integral = typename std::is_integral<T>;

template <class T>
using is_signed_int =
    typename std::conditional<is_integral<T>::value && std::is_signed<T>::value,
                              std::true_type, std::false_type>::type;

template <class T>
using is_unsigned_int =
    typename std::conditional<is_integral<T>::value &&
                                  std::is_unsigned<T>::value,
                              std::true_type, std::false_type>::type;

template <class T>
using to_unsigned =
    typename std::conditional<is_signed_int<T>::value, std::make_unsigned<T>,
                              std::common_type<T>>::type;

#endif

template <class T>
using is_signed_int_t = std::enable_if_t<is_signed_int<T>::value>;

template <class T>
using is_unsigned_int_t = std::enable_if_t<is_unsigned_int<T>::value>;

template <class T> using to_unsigned_t = typename to_unsigned<T>::type;

} // namespace internal

} // namespace atcoder

namespace atcoder {

namespace internal {

struct modint_base {};
struct static_modint_base : modint_base {};

template <class T> using is_modint = std::is_base_of<modint_base, T>;
template <class T> using is_modint_t = std::enable_if_t<is_modint<T>::value>;

} // namespace internal

template <int m, std::enable_if_t<(1 <= m)> * = nullptr>
struct static_modint : internal::static_modint_base {
    using mint = static_modint;

  public:
    static constexpr int mod() { return m; }
    static mint raw(int v) {
        mint x;
        x._v = v;
        return x;
    }

    static_modint() : _v(0) {}
    template <class T, internal::is_signed_int_t<T> * = nullptr>
    static_modint(T v) {
        long long x = (long long)(v % (long long)(umod()));
        if (x < 0)
            x += umod();
        _v = (unsigned int)(x);
    }
    template <class T, internal::is_unsigned_int_t<T> * = nullptr>
    static_modint(T v) {
        _v = (unsigned int)(v % umod());
    }

    unsigned int val() const { return _v; }

    mint &operator++() {
        _v++;
        if (_v == umod())
            _v = 0;
        return *this;
    }
    mint &operator--() {
        if (_v == 0)
            _v = umod();
        _v--;
        return *this;
    }
    mint operator++(int) {
        mint result = *this;
        ++*this;
        return result;
    }
    mint operator--(int) {
        mint result = *this;
        --*this;
        return result;
    }

    mint &operator+=(const mint &rhs) {
        _v += rhs._v;
        if (_v >= umod())
            _v -= umod();
        return *this;
    }
    mint &operator-=(const mint &rhs) {
        _v -= rhs._v;
        if (_v >= umod())
            _v += umod();
        return *this;
    }
    mint &operator*=(const mint &rhs) {
        unsigned long long z = _v;
        z *= rhs._v;
        _v = (unsigned int)(z % umod());
        return *this;
    }
    mint &operator/=(const mint &rhs) { return *this = *this * rhs.inv(); }

    mint operator+() const { return *this; }
    mint operator-() const { return mint() - *this; }

    mint pow(long long n) const {
        assert(0 <= n);
        mint x = *this, r = 1;
        while (n) {
            if (n & 1)
                r *= x;
            x *= x;
            n >>= 1;
        }
        return r;
    }
    mint inv() const {
        if (prime) {
            assert(_v);
            return pow(umod() - 2);
        } else {
            auto eg = internal::inv_gcd(_v, m);
            assert(eg.first == 1);
            return eg.second;
        }
    }

    friend mint operator+(const mint &lhs, const mint &rhs) {
        return mint(lhs) += rhs;
    }
    friend mint operator-(const mint &lhs, const mint &rhs) {
        return mint(lhs) -= rhs;
    }
    friend mint operator*(const mint &lhs, const mint &rhs) {
        return mint(lhs) *= rhs;
    }
    friend mint operator/(const mint &lhs, const mint &rhs) {
        return mint(lhs) /= rhs;
    }
    friend bool operator==(const mint &lhs, const mint &rhs) {
        return lhs._v == rhs._v;
    }
    friend bool operator!=(const mint &lhs, const mint &rhs) {
        return lhs._v != rhs._v;
    }

  private:
    unsigned int _v;
    static constexpr unsigned int umod() { return m; }
    static constexpr bool prime = internal::is_prime<m>;
};

template <int id> struct dynamic_modint : internal::modint_base {
    using mint = dynamic_modint;

  public:
    static int mod() { return (int)(bt.umod()); }
    static void set_mod(int m) {
        assert(1 <= m);
        bt = internal::barrett(m);
    }
    static mint raw(int v) {
        mint x;
        x._v = v;
        return x;
    }

    dynamic_modint() : _v(0) {}
    template <class T, internal::is_signed_int_t<T> * = nullptr>
    dynamic_modint(T v) {
        long long x = (long long)(v % (long long)(mod()));
        if (x < 0)
            x += mod();
        _v = (unsigned int)(x);
    }
    template <class T, internal::is_unsigned_int_t<T> * = nullptr>
    dynamic_modint(T v) {
        _v = (unsigned int)(v % mod());
    }

    unsigned int val() const { return _v; }

    mint &operator++() {
        _v++;
        if (_v == umod())
            _v = 0;
        return *this;
    }
    mint &operator--() {
        if (_v == 0)
            _v = umod();
        _v--;
        return *this;
    }
    mint operator++(int) {
        mint result = *this;
        ++*this;
        return result;
    }
    mint operator--(int) {
        mint result = *this;
        --*this;
        return result;
    }

    mint &operator+=(const mint &rhs) {
        _v += rhs._v;
        if (_v >= umod())
            _v -= umod();
        return *this;
    }
    mint &operator-=(const mint &rhs) {
        _v += mod() - rhs._v;
        if (_v >= umod())
            _v -= umod();
        return *this;
    }
    mint &operator*=(const mint &rhs) {
        _v = bt.mul(_v, rhs._v);
        return *this;
    }
    mint &operator/=(const mint &rhs) { return *this = *this * rhs.inv(); }

    mint operator+() const { return *this; }
    mint operator-() const { return mint() - *this; }

    mint pow(long long n) const {
        assert(0 <= n);
        mint x = *this, r = 1;
        while (n) {
            if (n & 1)
                r *= x;
            x *= x;
            n >>= 1;
        }
        return r;
    }
    mint inv() const {
        auto eg = internal::inv_gcd(_v, mod());
        assert(eg.first == 1);
        return eg.second;
    }

    friend mint operator+(const mint &lhs, const mint &rhs) {
        return mint(lhs) += rhs;
    }
    friend mint operator-(const mint &lhs, const mint &rhs) {
        return mint(lhs) -= rhs;
    }
    friend mint operator*(const mint &lhs, const mint &rhs) {
        return mint(lhs) *= rhs;
    }
    friend mint operator/(const mint &lhs, const mint &rhs) {
        return mint(lhs) /= rhs;
    }
    friend bool operator==(const mint &lhs, const mint &rhs) {
        return lhs._v == rhs._v;
    }
    friend bool operator!=(const mint &lhs, const mint &rhs) {
        return lhs._v != rhs._v;
    }

  private:
    unsigned int _v;
    static internal::barrett bt;
    static unsigned int umod() { return bt.umod(); }
};
template <int id> internal::barrett dynamic_modint<id>::bt(998244353);

using modint998244353 = static_modint<998244353>;
using modint1000000007 = static_modint<1000000007>;
using modint = dynamic_modint<-1>;

namespace internal {

template <class T>
using is_static_modint = std::is_base_of<internal::static_modint_base, T>;

template <class T>
using is_static_modint_t = std::enable_if_t<is_static_modint<T>::value>;

template <class> struct is_dynamic_modint : public std::false_type {};
template <int id>
struct is_dynamic_modint<dynamic_modint<id>> : public std::true_type {};

template <class T>
using is_dynamic_modint_t = std::enable_if_t<is_dynamic_modint<T>::value>;

} // namespace internal

} // namespace atcoder

using mint = atcoder::modint998244353;
#line 4 "cpplib/math/ACL_modint_base.hpp"

std::ostream &operator<<(std::ostream &lhs, const mint &rhs) noexcept {
    lhs << rhs.val();
    return lhs;
}
std::istream &operator>>(std::istream &lhs, mint &rhs) noexcept {
    long long x;
    lhs >> x;
    rhs = x;
    return lhs;
}

int MOD_NOW = -1;
int FACT_TABLE_SIZE = 0;
std::vector<mint> fact_table, fact_inv_table;

void update(int x) {
    if (MOD_NOW != mint::mod() || FACT_TABLE_SIZE == 0) {
        fact_table.assign(1, 1);
        fact_inv_table.assign(1, 1);
        FACT_TABLE_SIZE = 1;
        MOD_NOW = mint::mod();
    }
    while (FACT_TABLE_SIZE <= x) {
        fact_table.resize(FACT_TABLE_SIZE * 2);
        fact_inv_table.resize(FACT_TABLE_SIZE * 2);
        for (int i = FACT_TABLE_SIZE; i < FACT_TABLE_SIZE * 2; ++i) {
            fact_table[i] = fact_table[i - 1] * i;
        }
        fact_inv_table[FACT_TABLE_SIZE * 2 - 1] =
            fact_table[FACT_TABLE_SIZE * 2 - 1].inv();
        for (int i = FACT_TABLE_SIZE * 2 - 2; i >= FACT_TABLE_SIZE; --i) {
            fact_inv_table[i] = fact_inv_table[i + 1] * (i + 1);
        }
        FACT_TABLE_SIZE *= 2;
    }
}

inline mint fact(int x) {
    assert(x >= 0);
    update(x);
    return fact_table[x];
}
inline mint fact_inv(int x) {
    assert(x >= 0);
    update(x);
    return fact_inv_table[x];
}
inline mint comb(int x, int y) {
    if (x < 0 || x < y || y < 0)
        return 0;
    return fact(x) * fact_inv(y) * fact_inv(x - y);
}
inline mint perm(int x, int y) { return fact(x) * fact_inv(x - y); }

// x個のグループにy個のものを分ける場合の数
inline mint multi_comb(int x, int y) {
    if (y == 0 && x >= 0)
        return 1;
    if (y < 0 || x <= 0)
        return 0;
    return comb(x + y - 1, y);
}
#line 3 "cpplib/math/lagrange_interpolation.hpp"
/**
 * @brief ラグランジュ補完(連続点->一点)
 */

template <typename T> T lagrange_interpolation(std::vector<T> v, long long n) {
    long long k = v.size();
    if (n < k)
        return v[n];
    std::vector<T> tmp1(k + 1, 1), tmp2(k + 1, 1);
    T ans = 0;
    for (int i = 0; i < k; ++i)
        tmp1[i] = (i ? tmp1[i - 1] : T(1)) * (n - i);
    for (int i = k - 1; i >= 0; --i)
        tmp2[i] = (i < k - 1 ? tmp2[i + 1] : T(1)) * (n - i);
    for (int i = 0; i < k; ++i) {
        ans += v[i] * (i < k - 1 ? tmp2[i + 1] : 1) * (i ? tmp1[i - 1] : T(1)) /
               (fact(k - 1 - i) * fact(i) * T((k - 1 - i) % 2 ? -1 : 1));
    }
    return ans;
}
#line 5 "main.cpp"

void solve() {
    lint n, k;
    cin >> n >> k;
    vector<mint> v1(k + 3, 0), v2(k + 3, 0);
    rep(i, 1, k + 3) {
        v1[i] = v1[i - 1] + mint(i).pow(k);
        v2[i] = v2[i - 1] + mint(i).pow(k + 1);
    }
    mint ans = lagrange_interpolation<mint>(v1, n) * n -
               lagrange_interpolation<mint>(v2, n);
    vector<mint> tb = {
        1,         945896249, 826994544, 147972654, 718271290, 311054462,
        848172652, 487479281, 181218541, 225032295, 464016596, 303879624,
        711595889, 801978400, 274311861, 262505243, 197661226, 560969645,
        59654808,  844084429, 63299249,  656698209, 745706197, 782663844,
        722450722, 437503635, 974490943, 756414660, 100919583, 567153381,
        434731971, 992060846, 397327632, 588176542, 152285902, 561146832,
        410851918, 739984378, 631617451, 918814530, 55395755,  984167498,
        880949811, 904643816, 713793642, 44666331,  712775427, 443688906,
        488198727, 374504494, 15814281,  809754637, 581403016, 931134979,
        415434801, 733417940, 522329741, 396654552, 691138193, 924037483,
        565294571, 647279052, 93888746,  491863506, 860288574, 933267285,
        420593226, 601485588, 643768503, 139726730, 293833759, 963402916,
        983736712, 496456348, 270369543, 205793557, 946545391, 54554286,
        827540230, 533325452, 851627080, 695240733, 872441336, 641905269,
        107293455, 814887934, 659546511, 435069442, 36312125,  691840784,
        130777589, 586041601, 696055209, 627965301, 914253051, 159075500,
        818001905, 839514995, 613224734, 923597279, 0};
    ans *= tb[n / 10000000];
    rep(i, 1, n % 10000000) { ans *= n / 10000000 * 10000000 + i; }
    ans *= 2;
    cout << ans << endl;
}

int main() {
    // mint t=1;
    // rep(i,1,1000000001){
    //     if(i%10000000==0)cout<<t<<",";
    //     t*=i;
    // }

    solve();
    // lint t;cin>>t;while(t--)solve();
}