only rm when params.escape, rm space if possible which is added back or rm added space token

Author: vvhg1

examples/infill/infill.cpp

@@ -234,10 +234,11 @@ int main(int argc, char ** argv) {
     LOG("add_bos: %d\n", add_bos);
 
     bool suff_rm_leading_spc = params.escape;
-    if (suff_rm_leading_spc && params.input_suffix.find_first_of(" ") == 0 && params.input_suffix.size() > 1) {
-        params.input_suffix.erase(0, 1);
-        suff_rm_leading_spc = false;
-    }
+    // if (suff_rm_leading_spc && params.input_suffix.find_first_of(" ") == 0 && params.input_suffix.size() > 1) {
+    //     params.input_suffix.erase(0, 1);
+    //     suff_rm_leading_spc = false;
+    // }
+    suff_rm_leading_spc = true;
     std::vector<llama_token> embd_inp;
     std::vector<llama_token> inp_pfx = ::llama_tokenize(ctx, params.input_prefix, false);
     std::vector<llama_token> inp_sfx = ::llama_tokenize(ctx, params.input_suffix, false);