Skip to content
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

Add Command R chat template #6650

Merged
merged 4 commits into from
Apr 14, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
15 changes: 15 additions & 0 deletions llama.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -16476,6 +16476,21 @@ static int32_t llama_chat_apply_template_internal(
if (add_ass) {
ss << "### Response:\n";
}
} else if (tmpl == "command-r" || (tmpl.find("<|START_OF_TURN_TOKEN|>") != std::string::npos && tmpl.find("<|USER_TOKEN|>") != std::string::npos)) {
// CohereForAI/c4ai-command-r-plus
for (auto message : chat) {
std::string role(message->role);
if (role == "system") {
ss << "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>" << trim(message->content) << "<|END_OF_TURN_TOKEN|>";
} else if (role == "user") {
ss << "<|START_OF_TURN_TOKEN|><|USER_TOKEN|>" << trim(message->content) << "<|END_OF_TURN_TOKEN|>";
} else if (role == "assistant") {
ss << "<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>" << trim(message->content) << "<|END_OF_TURN_TOKEN|>";
}
}
if (add_ass) {
ss << "<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>";
}
} else {
// template not supported
return -1;
Expand Down
4 changes: 4 additions & 0 deletions tests/test-chat-template.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,8 @@ int main(void) {
// Orca-Vicuna
// No template included in tokenizer_config.json, so this template likely needs to be manually set.
"{%- for message in messages %}{%- if message['role'] == 'system' -%}{{-'SYSTEM: ' + message['content'] + '\n' -}}{%- else -%}{%- if message['role'] == 'user' -%}{{-'USER: ' + message['content'] + '\n'-}}{%- else -%}{{-'ASSISTANT: ' + message['content'] + '</s>\n' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{-'ASSISTANT:'-}}{%- endif -%}",
// CohereForAI/c4ai-command-r-plus
"{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
};
std::vector<std::string> expected_output = {
// teknium/OpenHermes-2.5-Mistral-7B
Expand All @@ -69,6 +71,8 @@ int main(void) {
"You are a helpful assistant\n\nUSER: Hello\nASSISTANT: Hi there</s>\nUSER: Who are you\nASSISTANT: I am an assistant </s>\nUSER: Another question\nASSISTANT:",
// Orca-Vicuna
"SYSTEM: You are a helpful assistant\nUSER: Hello\nASSISTANT: Hi there</s>\nUSER: Who are you\nASSISTANT: I am an assistant </s>\nUSER: Another question\nASSISTANT:",
// CohereForAI/c4ai-command-r-plus
"<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>You are a helpful assistant<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>Hi there<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Who are you<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>I am an assistant<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Another question<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>",
};
std::vector<char> formatted_chat(1024);
int32_t res;
Expand Down