root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-28 04:14:35 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

infill tokens correction

Browse Source
This commit is contained in:
vvhg1 2023-10-06 18:26:18 +02:00
parent c97f01c362
commit dfeda32abd
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
examples/infill/infill.cpp
View File

@ -234,9 +234,12 @@ int main(int argc, char ** argv) {
LOG("add_bos: %d\n", add_bos);
std::vector<llama_token> embd_inp;
std::vector<llama_token> inp_pfx = ::llama_tokenize(ctx, params.input_prefix, add_bos);
std::vector<llama_token> inp_sfx = ::llama_tokenize(ctx, params.input_suffix, add_bos);
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);
inp_pfx.insert(inp_pfx.begin(), llama_token_prefix(ctx));
if (add_bos) {
inp_pfx.insert(inp_pfx.begin(), llama_token_bos(ctx));
}
inp_sfx.insert(inp_sfx.begin(), llama_token_suffix(ctx));
embd_inp = inp_pfx;
embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end());