#pragma GCC optimize("O3")
#pragma GCC optimize(2)
#pragma GCC optimize(3)
#pragma GCC optimize("Ofast")
#pragma GCC optimize("inline")
#pragma GCC optimize("-fgcse")
#pragma GCC optimize("-fgcse-lm")
#pragma GCC optimize("-fipa-sra")
#pragma GCC optimize("-ftree-pre")
#pragma GCC optimize("-ftree-vrp")
#pragma GCC optimize("-fpeephole2")
#pragma GCC optimize("-ffast-math")
#pragma GCC optimize("-fsched-spec")
#pragma GCC optimize("unroll-loops")
#pragma GCC optimize("-falign-jumps")
#pragma GCC optimize("-falign-loops")	
#pragma GCC optimize("-falign-labels")
#pragma GCC optimize("-fdevirtualize")
#pragma GCC optimize("-fcaller-saves")
#pragma GCC optimize("-fcrossjumping") 
#pragma GCC optimize("-fthread-jumps")
#pragma GCC optimize("-funroll-loops")
#pragma GCC optimize("-freorder-blocks")
#pragma GCC optimize("-fschedule-insns")
#pragma GCC optimize("inline-functions")
#pragma GCC optimize("-ftree-tail-merge")
#pragma GCC optimize("-fschedule-insns2")
#pragma GCC optimize("-fstrict-aliasing")
#pragma GCC optimize("-falign-functions")
#pragma GCC optimize("-fcse-follow-jumps")
#pragma GCC optimize("-fsched-interblock")
#pragma GCC optimize("-fpartial-inlining")
#pragma GCC optimize("no-stack-protector")
#pragma GCC optimize("-freorder-functions")
#pragma GCC optimize("-findirect-inlining")
#pragma GCC optimize("-fhoist-adjacent-loads")
#pragma GCC optimize("-frerun-cse-after-loop")
#pragma GCC optimize("inline-small-functions")
#pragma GCC optimize("-finline-small-functions")
#pragma GCC optimize("-ftree-switch-conversion")
#pragma GCC optimize("-foptimize-sibling-calls")
#pragma GCC optimize("-fexpensive-optimizations")
#pragma GCC optimize("inline-functions-called-once")
#pragma GCC optimize("-fdelete-null-pointer-checks")
#pragma GCC optimize("Ofast")

#include <bits/stdc++.h>
 
using namespace std;
 
const long long int MOD = 1e9 + 7;
long long int f[2000001];
long long int invf[2000001];
 
long long int mypow(long long int x,long long int n)
{
	long long int res = 1;
	while(n > 0)
	{
		if(n%2==1)
		{
			res*=x;
			res%=MOD;
		}
		x*=x;
		x%=MOD;
		n/=2;
	}
	return res;
}

long long int calc(long long int n, long long int k)
{
	if(n==0) return 0;
	vector < pair<long long int,long long int> > v; 
	long long int sum = 0;
 
	for(int i=1;i<=k+2;i++)
	{
		sum += mypow(i,k);
		sum%=MOD;
		v.push_back(make_pair(i,sum));
	}	
 
	if(n <= k+2)
	{
		return v[n-1].second;
	}
	long long int A = 1;
	int flag = 0;
	for(int i=0;i<v.size();i++)
	{
		long long int a = n - v[i].first;
		if(a < 0)
		{
			flag++;
			flag%=2;
		}
		a = abs(a);
		a%=MOD;
		A*=a;
		A%=MOD;
	}
 
	long long int res = 0;
 
	for(int i=0;i<v.size();i++)
	{
		int fflag = flag;
		long long int a = n - v[i].first;
		if(a < 0)
		{
			fflag-=1;
			fflag%=2;
			if(fflag < 0) fflag += 2;
		}
		a = abs(a);
		a%=MOD;
		long long int AA = A;
		AA*=mypow(a,MOD-2);
		AA%=MOD;
		//cout << v[i].first << ' ' << a << ' ' << A << ' ' << AA << ' ' << mypow(a,MOD-2) << '\n';
		//cout << A*mypow(a,MOD-2) << '\n';
		long long int L = v[i].first - 1;
		long long int R = (k+2) - v[i].first;
		fflag+=R;
		fflag%=2;
		long long int B = invf[L];
		B*=invf[R];
		B%=MOD;
		long long int val = AA;
		val*=B;
		val%=MOD;
		val*=v[i].second;
		val%=MOD;
		//cout << v[i].first << ' ' << val << '\n';
		if(fflag==0)
		{
			res += val;
			res%=MOD;
		}
		else
		{
			res -= val;
			res%=MOD;
			if(res < 0) res += MOD;
		}
	}
 
	return res;		
}
int main(void)
{
	cin.tie(0);
	ios::sync_with_stdio(false);
 
	f[0] = 1;
	for(int i=1;i<=2000000;i++)
	{
		f[i] = i*f[i-1];
		f[i]%=MOD;
	}
 
	invf[2000000] = mypow(f[2000000],MOD-2);
 
	for(int i=2000000;i>0;i--)
	{
		invf[i-1] = invf[i]*i;
		invf[i-1]%=MOD;
	}

	long long int n,k;
	
	cin >> n >> k;

	long long int res = calc(n,k);

	cout << res << '\n';
	
	return 0;
}