#include <bits/stdc++.h>
#include <math.h>

#include <algorithm>
#include <array>
#include <atcoder/all>
#include <bitset>
#include <iomanip>
#include <iostream>
#include <map>
#include <queue>
#include <sstream>
#include <vector>

using namespace std;
using namespace atcoder;

using Graph = vector<vector<int>>;

using ll = long long;
typedef pair<ll, ll> P_ll;
typedef pair<int, int> P;

const ll INF_ll = 1e17;
const int INF = 1e8;
template <class T>
bool chmax(T& a, const T& b) {
  if (a < b) {
    a = b;
    return 1;
  }
  return 0;
}
template <class T>
bool chmin(T& a, const T& b) {
  if (b < a) {
    a = b;
    return 1;
  }
  return 0;
}
template <typename T>
using min_priority_queue = priority_queue<T, vector<T>, greater<T>>;

int main() {
  ll P, K;
  cin >> P >> K;
  vector<vector<modint1000000007>> dp(K + 1, vector<modint1000000007>(2, 0));
  dp[0][0] = 1;
  for (int i = 0; i < K; i++) {
    {  //+
      dp[i + 1][0] += dp[i][0];
      dp[i + 1][0] += dp[i][1];

      dp[i + 1][1] += dp[i][1] * (P - 1);
      dp[i + 1][1] += dp[i][0] * (P - 1);
    }
    {  // x
      dp[i + 1][0] += dp[i][0] * P;
      dp[i + 1][0] += dp[i][1];

      dp[i + 1][1] += dp[i][1] * (P - 1);
    }
  }
  cout << dp[K][0].val() << endl;

  return 0;
}