#include<bits/stdc++.h>
#define ll long long
#define vi vector<int>
#define vll vector<ll>
#define eb emplace_back
#define pb push_back
#define all(v) v.begin(),v.end()
#define rall(v) v.rbegin(),v.rend()
#define sz(v) ((int)v.size())
#define pii pair<int,int>
#define pll pair<ll,ll>
#define fi first
#define se second
#define umap unordered_map
#define uset unordered_set
#define mset multiset
#define ui unsigned int
#define ull unsigned ll
#define i128 __int128
using namespace std;

namespace qiqi {
	const int P = 1e9+7;
	struct BIT {
		int n; vll a; BIT(int n):n(n),a(n,0) {}
		int lbt(int x) {return x&(-x);}
		void upd(int x,int k) {
			for (int i = x+1; i <= n; i += lbt(i)) {
				a[i-1] = (a[i-1]+k)%P;
			}
		}
		int qry(int x) {
			ll k = 0;
			for (int i = x; i > 0; i -= lbt(i)) {
				k += a[i-1];
			}
			return k%P;
		}
	};
	void main() {
		int n;
		cin >> n;
		vi p(n);
		for (int i = 0; i < n; i++) {
			cin >> p[i]; p[i]--;
		}
		vector<BIT> bit(n+1,n+1);
		bit[0].upd(0,1);
		for (int i = 0; i < n; i++) {
			for (int j = i; j >= 0; j--) {
				bit[j+1].upd(p[i]+1,bit[j].qry(p[i]+1));
			}
		}
		vector<vll> s(n+1,vll(n+1)); s[1][1] = 1;
		for (int i = 2; i <= n; i++) {
			for (int j = 1; j <= i; j++) {
				s[i][j] = (s[i-1][j-1]+j*s[i-1][j])%P;
			}
		}
		vll fac(n+1); fac[0] = 1;
		for (int i = 1; i <= n; i++) {
			fac[i] = i*fac[i-1]%P;
		}
		int ans = 0;
		for (int i = 1; i <= n; i++) {
			ll k = bit[i].qry(n+1);
			ans = (ans+k*fac[i]%P*s[n][i])%P;
		}
		cout << ans << '\n';
	}
}

int main() {
//	clock_t st = clock();
//	freopen("test.in","r",stdin);
//	freopen("test.out","w",stdout);
	ios::sync_with_stdio(false);
	cin.tie(nullptr);

	int T = 1;
//	cin >> T;
	while (T--) {
		qiqi::main();
	}

//	cout << (double)(clock()-st)/CLOCKS_PER_SEC;
	return 0;
}