Skip to content

tools/main: llama-cli: prevent spurious assistant token (#13402) #16202

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Sep 29, 2025
Merged

tools/main: llama-cli: prevent spurious assistant token (#13402) #16202

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bcf14fd
tools/main: llama-cli: prevent spurious assistant token (#13402)
vinkal-chudgar Sep 22, 2025
2f16ea6
Update tools/main/main.cpp
vinkal-chudgar Sep 24, 2025
61b76c3
tools/main: remove outdated comment
vinkal-chudgar Sep 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 4 additions & 3 deletions tools/main/main.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -706,6 +706,10 @@ int main(int argc, char ** argv) {
// LOG_DBG("last: %s\n", string_from(ctx, smpl->prev.to_vector()).c_str());

embd.push_back(id);

if (params.conversation_mode && !waiting_for_first_input && !llama_vocab_is_eog(vocab, id)) {
assistant_ss << common_token_to_piece(ctx, id, false);
}

// echo this to console
input_echo = true;
Expand Down Expand Up @@ -826,9 +830,6 @@ int main(int argc, char ** argv) {

// if current token is not EOG, we add it to current assistant message
if (params.conversation_mode && !waiting_for_first_input) {
const auto id = common_sampler_last(smpl);
assistant_ss << common_token_to_piece(ctx, id, false);

if (!prompt.empty()) {
prompt.clear();
is_interacting = false;
Expand Down
Loading