#include <iostream>
#include <algorithm>
#include <string>
#include <vector>
#include <cmath>
#include <map>
#include <queue>
#include <iomanip>
#include <set>
#include <tuple>
#define mkp make_pair
#define mkt make_tuple
#define rep(i,n) for(int i = 0; i < (n); ++i)
#define all(v) v.begin(),v.end()
using namespace std;
typedef long long ll;
const ll MOD=1e9+7;
template<class T> void chmin(T &a,const T &b){if(a>b) a=b;}
template<class T> void chmax(T &a,const T &b){if(a<b) a=b;}

#define MAX_N 1000010
ll inv[MAX_N+10],fac[MAX_N+10],ifac[MAX_N+10];

void setComb(){
  inv[0]=1;inv[1]=1;fac[1]=1;ifac[1]=1;fac[0]=1;ifac[0]=1;
  for(int i=2;i<MAX_N;i++){
    inv[i]=(-MOD/i)*inv[MOD%i]%MOD;
    fac[i]=fac[i-1]*i%MOD;
    ifac[i]=ifac[i-1]*inv[i]%MOD;

    inv[i]=(inv[i]+MOD)%MOD;
    fac[i]=(fac[i]+MOD)%MOD;
    ifac[i]=(ifac[i]+MOD)%MOD;
  }
  return;
}

ll comb(ll n,ll k){
  if(n<k||n<0||k<0) return 0;
  else return ((fac[n]*ifac[k]%MOD*ifac[n-k]%MOD+MOD)%MOD);
}

ll hcomb(ll n,ll r){// this size is really ok??
  if(n==0&&r==0) return 1;
  else if(n<0||r<0) return 0;
  else return comb(n+r-1,r);
}

ll mod_pow(ll x,ll n){
  x%=MOD;
  ll res=1;
  while(n>0){
    if(n&1) res=res*x%MOD;
    x=x*x%MOD;
    n>>=1;
  }
  return res;
}

void add(ll &a,ll b){
  a=(a+b)%MOD;
}

void mul(ll &a,ll b){
  a%=MOD;b%=MOD;
  a=a*b%MOD;
}

int main(){
  cin.tie(0);
  ios::sync_with_stdio(false);

  int N;
  ll K;
  cin>>N>>K;
  vector<ll> A(N);
  rep(i,N) cin>>A[i];

  setComb();

  vector<ll> H(N+1,0);
  H[1]=1;
  for(int i=2;i<=N;i++){
    H[i]=H[i-1];
    mul(H[i],K+i-1);
    mul(H[i],inv[i-1]);
  }

  ll ans=0;
  for(int i=0;i<N;i++){
    ll coef=H[i+1];
    mul(coef,H[N-i]);
    ll res=A[i];
    mul(res,coef);
    add(ans,res);
  }

  cout<<ans<<endl;

  return 0;
}