Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-23 01:49:18 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama : add llama-3 chat template (#6751)

Browse Source 
* Added llama-3 chat template

* Update llama.cpp

Co-authored-by: Samuel Tallet <36248671+SamuelTallet@users.noreply.github.com>

* Update llama.cpp

Co-authored-by: Samuel Tallet <36248671+SamuelTallet@users.noreply.github.com>

* Update tests/test-chat-template.cpp

Co-authored-by: Samuel Tallet <36248671+SamuelTallet@users.noreply.github.com>

* Added EOS stop sequence according to https://github.com/ggerganov/llama.cpp/pull/6751#issuecomment-2065602862

* Removed adding of BOS token before first message

* Removed bos token from expected output from llama-3

* Update tests/test-chat-template.cpp

Co-authored-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com>

* Update tests/test-chat-template.cpp

Co-authored-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com>

* Added <|end_of_text|> as another stop token

* Reverted last change of adding the end_of_text stop word for llama 3

---------

Co-authored-by: Wouter Tichelaar <tichelaarw@spar.net>
Co-authored-by: Samuel Tallet <36248671+SamuelTallet@users.noreply.github.com>
Co-authored-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Wouter 2024-04-21 15:03:39 +02:00 committed by GitHub
parent c1386c936e
commit 7dbdba5690
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llama.cpp
View File

@ -17247,6 +17247,15 @@ static int32_t llama_chat_apply_template_internal(
if (add_ass) {
ss << "<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>";
}
} else if (tmpl == "llama3" || (tmpl.find("<|start_header_id|>") != std::string::npos && tmpl.find("<|end_header_id|>") != std::string::npos)) {
// Llama 3
for (auto message : chat) {
std::string role(message->role);
ss << "<|start_header_id|>" << role << "<|end_header_id|>\n\n" << trim(message->content) << "<|eot_id|>";
}
if (add_ass) {
ss << "<|start_header_id|>assistant<|end_header_id|>\n\n";
}
} else {
// template not supported
return -1;

6
tests/test-chat-template.cpp
View File

@ -46,7 +46,9 @@ int main(void) {
// 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 %}"
"{{ 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 %}",
// Llama-3
"{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
};
std::vector<std::string> expected_output = {
// teknium/OpenHermes-2.5-Mistral-7B
@ -73,6 +75,8 @@ int main(void) {
"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|>",
// Llama 3
"<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHello<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nHi there<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWho are you<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nI am an assistant<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nAnother question<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
};
std::vector<char> formatted_chat(1024);
int32_t res;