#include <bits/stdc++.h>

using namespace std;
typedef long long ll;
typedef pair<ll, ll> p_ll;

template<class T>
void debug(T itr1, T itr2) { auto now = itr1; while(now<itr2) { cout << *now << " "; now++; } cout << endl; }
#define repr(i,from,to) for (ll i=(ll)from; i<(ll)to; i++)
#define all(vec) vec.begin(), vec.end()
#define rep(i,N) repr(i,0,N)
#define per(i,N) for (int i=(int)N-1; i>=0; i--)

const ll MOD = pow(10,9)+7;
const ll LLINF = pow(2,61)-1;
const int INF = pow(2,30)-1;

vector<ll> fac;
void c_fac(int x=pow(10,6)+10) { fac.resize(x,true); rep(i,x) fac[i] = i ? (fac[i-1]*i)%MOD : 1; }
ll inv(ll a, ll m=MOD) { ll b = m, x = 1, y = 0; while (b!=0) { int d = a/b; a -= b*d; swap(a,b); x -= y*d; swap(x,y); } return (x+m)%m; }
ll nck(ll n, ll k) { return fac[n]*inv(fac[k]*fac[n-k]%MOD)%MOD; }
ll gcd(ll a, ll b) { if (a<b) swap(a,b); return b==0 ? a : gcd(b, a%b); }
ll lcm(ll a, ll b) { return a/gcd(a,b)*b; }


int main() {
  ll N, K; cin >> N >> K;
  ll A[N]; rep(i,N) cin >> A[i];

  ll l[N] = {}; rep(i,N) l[i] = i==0 ? 1 : l[i-1]*((i+K-1)*inv(i)%MOD)%MOD;
  ll sl[N] = {}; rep(i,N) sl[i] = i==0 ? l[i] : sl[i-1] + l[i];
  debug(l,l+N); debug(sl,sl+N); cout << endl;

  // rep(i,N) cout << sl[i] << "*" << sl[(N-1)-i] << endl;
  ll result = 0; rep(i,N) result = (result+(sl[i]*sl[(N-1)-i])%MOD*A[i]%MOD) % MOD;
  cout << result << endl;
  return 0;
}