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

llama : add Orion chat template (#6066)

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-03-15 09:44:57 +01:00 committed by GitHub
parent b0bc9f4a9d
commit aab606a11f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 24 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
llama.cpp
View file

@ -14242,6 +14242,26 @@ static int32_t llama_chat_apply_template_internal(
if (add_ass) {
ss << "<start_of_turn>model\n";
}
} else if (tmpl == "orion" || tmpl.find("'\\n\\nAssistant: ' + eos_token") != std::string::npos) {
// OrionStarAI/Orion-14B-Chat
std::string system_prompt = "";
for (auto message : chat) {
std::string role(message->role);
if (role == "system") {
// there is no system message support, we will merge it with user prompt
system_prompt = message->content;
continue;
} else if (role == "user") {
ss << "Human: ";
if (!system_prompt.empty()) {
ss << system_prompt << "\n\n";
system_prompt = "";
}
ss << message->content << "\n\nAssistant: </s>";
} else {
ss << message->content << "</s>";
}
}
} else {
// template not supported
return -1;

4
tests/test-chat-template.cpp
View file

@ -31,6 +31,8 @@ int main(void) {
"{% for message in messages %}{{bos_token + message['role'] + '\\n' + message['content'] + eos_token + '\\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\\n' }}{% endif %}",
// google/gemma-7b-it
"{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\\n' + message['content'] | trim + '<end_of_turn>\\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\\n'}}{% endif %}",
// OrionStarAI/Orion-14B-Chat
"{% for message in messages %}{% if loop.first %}{{ bos_token }}{% endif %}{% if message['role'] == 'user' %}{{ 'Human: ' + message['content'] + '\\n\\nAssistant: ' + eos_token }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}",
};
std::vector<std::string> expected_output = {
// teknium/OpenHermes-2.5-Mistral-7B
@ -45,6 +47,8 @@ int main(void) {
"system\nYou are a helpful assistant</s>\n<s>user\nHello</s>\n<s>assistant\nHi there</s>\n<s>user\nWho are you</s>\n<s>assistant\n I am an assistant </s>\n<s>user\nAnother question</s>\n<s>assistant\n",
// google/gemma-7b-it
"<start_of_turn>user\nYou are a helpful assistant\n\nHello<end_of_turn>\n<start_of_turn>model\nHi there<end_of_turn>\n<start_of_turn>user\nWho are you<end_of_turn>\n<start_of_turn>model\nI am an assistant<end_of_turn>\n<start_of_turn>user\nAnother question<end_of_turn>\n<start_of_turn>model\n",
// OrionStarAI/Orion-14B-Chat
"Human: You are a helpful assistant\n\nHello\n\nAssistant: </s>Hi there</s>Human: Who are you\n\nAssistant: </s> I am an assistant </s>Human: Another question\n\nAssistant: </s>",
};
std::vector<char> formatted_chat(1024);
int32_t res;