#pragma GCC target("avx")
#pragma GCC optimize("O3")
#pragma GCC optimize("unroll-loops")
#include <bits/stdc++.h>
using namespace std;
using ll = long long;
using ld = long double;
using VI = vector<int>;
using VL = vector<ll>;
using VS = vector<string>;
template<class T> using PQ = priority_queue<T, vector<T>, greater<T>>;
#define FOR(i,a,n) for(int (i)=(a);(i)<(n);++(i))
#define eFOR(i,a,n) for(int (i)=(a);(i)<=(n);++(i))
#define rFOR(i,a,n) for(int (i)=(n)-1;(i)>=(a);--(i))
#define erFOR(i,a,n) for(int (i)=(n);(i)>=(a);--(i))
#define each(i, a) for(auto &i : a)
#define SORT(i) sort((i).begin(),(i).end())
#define rSORT(i,a) sort((i).begin(),(i).end(),(a))
#define all(i) (i).begin(),(i).end()
#define out(y,x) ((y) < 0 || h <= (y) || (x) < 0 || w <= (x))
#define line cout << "-----------------------------\n" 
#define ENDL(i,n) ((i) == (n) - 1 ? "\n" : " ")
constexpr ll INF = 1000000000;
constexpr ll LLINF = 1LL << 60;
constexpr ll mod = 1000000007;
constexpr ll MOD = 998244353;
constexpr ld eps = 1e-10;
constexpr ld pi = 3.1415926535897932;
template<class T>inline bool chmax(T& a, const T& b) { if (a < b) { a = b; return true; }return false; }
template<class T>inline bool chmin(T& a, const T& b) { if (a > b) { a = b; return true; }return false; }
inline void init() { cin.tie(nullptr); cout.tie(nullptr); ios::sync_with_stdio(false); cout << fixed << setprecision(15); }
template<class T>inline istream& operator>>(istream& is, vector<T>& v) { for (auto& a : v)is >> a; return is; }
template<class T, class U>inline istream& operator>>(istream& is, pair<T, U>& p) { is >> p.first >> p.second; return is; }
template<class T>inline vector<T> vec(size_t a) { return vector<T>(a); }
template<class T>inline vector<T> defvec(T def, size_t a) { return vector<T>(a, def); }
template<class T, class... Ts>inline auto vec(size_t a, Ts... ts) { return vector<decltype(vec<T>(ts...))>(a, vec<T>(ts...)); }
template<class T, class... Ts>inline auto defvec(T def, size_t a, Ts... ts) { return vector<decltype(defvec<T>(def, ts...))>(a, defvec<T>(def, ts...)); }
inline void print() { cout << "\n"; }
template<class T, class... Ts>inline void print(const T& a, const Ts&... ts) { cout << a << " "; print(ts...); }
template<class T>inline void print(const vector<T>& v) { for (int i = 0; i < v.size(); ++i)cout << v[i] << (i == v.size() - 1 ? "\n" : " "); }
template<class T>inline void print(const vector<vector<T>>& v) { for (auto& a : v)print(a); }
string reversed(const string& s) { string t = s; reverse(all(t)); return t; }

struct matrix {
    int n, m;
    vector<vector<ll>> dat;
    matrix(const vector<vector<ll>>& _a) : dat(_a) {
        n = dat.size(), m = dat.front().size();
    }
    matrix(const int& _n, const int& _m) : n(_n), m(_m) {
        dat = vec<ll>(n, m);
    }
    matrix() {}

    matrix operator*=(const matrix& a) {
        assert(m == a.n);
        matrix ret(vec<ll>(n, a.m));
        FOR(i, 0, n)FOR(k, 0, m)FOR(j, 0, a.m) {
            ret[i][j] += dat[i][k] * a.dat[k][j] % mod;
            if (mod <= ret[i][j])ret[i][j] -= mod;
        }
        return *this = ret;
    }
    matrix operator*(const matrix& a) { return matrix(*this) *= a; }

    matrix pow(ll k) const {
        assert(n == m);
        matrix ret(vec<ll>(n, n)), a(dat);
        FOR(i, 0, n)ret[i][i] = 1;
        for (; 0 < k; k >>= 1) {
            if (k & 1)ret*= a;
            a*= a;
        }
        return ret;
    }

    ll sum() const {
        ll ret = 0;
        FOR(i, 0, n)FOR(j, 0, m) {
            ret += dat[i][j];
            if (mod <= ret)ret -= mod;
        }
        return ret;
    }

    vector<ll>& operator[](int i) { return dat[i]; }
};

int main() {
    init();

    int m, k; cin >> m >> k;

    matrix x(m, m), y(m, m);
    x[0][0] = 1;
    FOR(i, 0, m)FOR(j, 0, m) {
        ++y[i][(i + j) % m];
        ++y[i][(i * j) % m];
    }

    print((x * y.pow(k))[0][0]);
}