@@ -74,8 +74,6 @@ int main(int argc, char ** argv) {
74
74
auto next_token = llama_sampler_sample (smpl, ctx, -1 );
75
75
auto next_token_str = llama_token_to_piece (ctx, next_token);
76
76
77
- llama_sampler_accept (smpl, next_token);
78
-
79
77
printf (" %s" , next_token_str.c_str ());
80
78
result0 += next_token_str;
81
79
@@ -132,8 +130,6 @@ int main(int argc, char ** argv) {
132
130
auto next_token = llama_sampler_sample (smpl2, ctx2, -1 );
133
131
auto next_token_str = llama_token_to_piece (ctx2, next_token);
134
132
135
- llama_sampler_accept (smpl2, next_token);
136
-
137
133
printf (" %s" , next_token_str.c_str ());
138
134
result1 += next_token_str;
139
135
@@ -222,8 +218,6 @@ int main(int argc, char ** argv) {
222
218
auto next_token = llama_sampler_sample (smpl3, ctx3, -1 );
223
219
auto next_token_str = llama_token_to_piece (ctx3, next_token);
224
220
225
- llama_sampler_accept (smpl3, next_token);
226
-
227
221
printf (" %s" , next_token_str.c_str ());
228
222
result2 += next_token_str;
229
223
0 commit comments