Skip to content

Fix chatml fallback for unsupported builtin templates (when --jinja not enabled) #11533

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.

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 1 commit into from
Jan 31, 2025
Merged
Changes from all commits
Commits
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
15 changes: 6 additions & 9 deletions examples/server/server.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -1804,7 +1804,12 @@ struct server_context {
llama_init_dft.context.reset();
}

chat_templates = common_chat_templates_from_model(model, params_base.chat_template);
if (params_base.chat_template.empty() && !validate_builtin_chat_template(params.use_jinja)) {
LOG_WRN("%s: The chat template that comes with this model is not yet supported, falling back to chatml. This may cause the model to output suboptimal responses\n", __func__);
chat_templates = common_chat_templates_from_model(model, "chatml");
} else {
chat_templates = common_chat_templates_from_model(model, params_base.chat_template);
}
GGML_ASSERT(chat_templates.template_default.get() != nullptr);

return true;
Expand Down Expand Up @@ -4374,14 +4379,6 @@ int main(int argc, char ** argv) {

LOG_INF("%s: model loaded\n", __func__);

// if a custom chat template is not supplied, we will use the one that comes with the model (if any)
if (params.chat_template.empty()) {
if (!ctx_server.validate_builtin_chat_template(params.use_jinja)) {
LOG_WRN("%s: The chat template that comes with this model is not yet supported, falling back to chatml. This may cause the model to output suboptimal responses\n", __func__);
params.chat_template = "chatml";
}
}

// print sample chat example to make it clear which template is used
LOG_INF("%s: chat template, chat_template: %s, example_format: '%s'\n", __func__,
ctx_server.chat_templates.template_default->source().c_str(),
Expand Down
Loading