Add chat template for alpaca
This commit is contained in:
parent
ce48a6e4de
commit
f1a3b12ced
2 changed files with 23 additions and 2 deletions
16
llama.cpp
16
llama.cpp
|
@ -15733,6 +15733,22 @@ static int32_t llama_chat_apply_template_internal(
|
||||||
if (add_ass) {
|
if (add_ass) {
|
||||||
ss << "ASSISTANT:";
|
ss << "ASSISTANT:";
|
||||||
}
|
}
|
||||||
|
} else if (tmpl == "alpaca" || tmpl.find("### Instruction:\\n") != std::string::npos) {
|
||||||
|
// wxjiao/alpaca-7b, deepseek-ai/deepseek-coder-33b-instruct
|
||||||
|
for (auto message : chat) {
|
||||||
|
std::string role(message->role);
|
||||||
|
if (role == "system") {
|
||||||
|
ss << message->content << "\n\n";
|
||||||
|
} else if (role == "user") {
|
||||||
|
ss << "### Instruction:\n" << message->content << "\n\n";
|
||||||
|
} else if (role == "assistant") {
|
||||||
|
ss << "### Response:\n" << message->content << "\n\n";
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if (add_ass) {
|
||||||
|
ss << "### Response:\n";
|
||||||
|
}
|
||||||
|
|
||||||
} else {
|
} else {
|
||||||
// template not supported
|
// template not supported
|
||||||
return -1;
|
return -1;
|
||||||
|
|
|
@ -40,7 +40,10 @@ int main(void) {
|
||||||
"{%- for message in messages %}{%- if message['role'] == 'system' -%}{{- '' + message['content'] + '\n\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 -%}",
|
"{%- for message in messages %}{%- if message['role'] == 'system' -%}{{- '' + message['content'] + '\n\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 -%}",
|
||||||
// Orca-Vicuna
|
// Orca-Vicuna
|
||||||
// No template included in config_tokenizer.json; extracted from: https://github.com/oobabooga/text-generation-webui/blob/main/instruction-templates/Orca-Vicuna.yaml
|
// No template included in config_tokenizer.json; extracted from: https://github.com/oobabooga/text-generation-webui/blob/main/instruction-templates/Orca-Vicuna.yaml
|
||||||
"{%- 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 -%}"
|
"{%- 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 -%}",
|
||||||
|
// wxjiao/alpaca-7b, deepseek-ai/deepseek-coder-33b-instruct
|
||||||
|
// No original Alpaca template Jinja, so using DeepSeek's instead
|
||||||
|
"{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}"
|
||||||
};
|
};
|
||||||
std::vector<std::string> expected_output = {
|
std::vector<std::string> expected_output = {
|
||||||
// teknium/OpenHermes-2.5-Mistral-7B
|
// teknium/OpenHermes-2.5-Mistral-7B
|
||||||
|
@ -62,7 +65,9 @@ int main(void) {
|
||||||
// eachadea/vicuna-13b-1.1
|
// eachadea/vicuna-13b-1.1
|
||||||
"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:",
|
"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
|
// 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:"
|
"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:",
|
||||||
|
// wxjiao/alpaca-7b, deepseek-ai/deepseek-coder-33b-instruct
|
||||||
|
"You are a helpful assistant\n\n### Instruction:\nHello\n\n### Response:\nHi there\n\n### Instruction:\nWho are you\n\n### Response:\n I am an assistant \n\n### Instruction:\nAnother question\n\n### Response:\n",
|
||||||
};
|
};
|
||||||
std::vector<char> formatted_chat(1024);
|
std::vector<char> formatted_chat(1024);
|
||||||
int32_t res;
|
int32_t res;
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue