Skip to content

feat: add audio content blocks for Gemma multimodal prompts in model_mm #2240

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

Open
cliu1003 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: add audio content blocks for Gemma multimodal prompts in model_mm #2240

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 6 additions & 1 deletion examples/c/src/common.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -476,14 +476,19 @@ nlohmann::ordered_json GetUserContent(const std::string& model_type, int num_ima
content_json = nlohmann::ordered_json(content);

} else {
// Gemma-3 style: structured content
// Gemma-style structured content (Gemma-3 / Gemma-4)
content_json = nlohmann::ordered_json::array();

// Add N image blocks
for (int i = 0; i < num_images; i++) {
content_json.push_back(nlohmann::ordered_json::object({{"type", "image"}}));
}

// Add N audio blocks (e.g. Gemma-4 audio support)
for (int i = 0; i < num_audios; i++) {
content_json.push_back(nlohmann::ordered_json::object({{"type", "audio"}}));
}

// Always add a text block (with the user prompt)
content_json.push_back(nlohmann::ordered_json::object({{"type", "text"}, {"text", prompt}}));
}
Expand Down
Loading