haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

used precomputed token text for grammar sample

Browse source
This commit is contained in:
marcus 2023-12-04 13:30:27 -08:00
parent 911a871968
commit 5dd1f45e1d
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -7361,7 +7361,7 @@ void llama_sample_grammar(struct llama_context * ctx, llama_token_data_array * c
for (size_t i = 0; i < candidates->size; ++i) {
const llama_token id = candidates->data[i].id;
const std::string piece = llama_token_to_piece(ctx, id);
const std::string piece = ctx->model.vocab.id_to_token[id].text;
if (id == eos) {
if (!allow_eos) {
candidates->data[i].logit = -INFINITY;