diff --git a/tests/test-chat-template.cpp b/tests/test-chat-template.cpp index f063ba15f..96b136908 100644 --- a/tests/test-chat-template.cpp +++ b/tests/test-chat-template.cpp @@ -33,8 +33,14 @@ int main(void) { "{% 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 %}{{ '' + role + '\\n' + message['content'] | trim + '\\n' }}{% endfor %}{% if add_generation_prompt %}{{'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 %}", - // openchat/openchat-3.5-0106 - "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}" + // openchat/openchat-3.5-0106, + "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}", + // eachadea/vicuna-13b-1.1, + // No template included in config_tokenizer.json; extracted from https://github.com/oobabooga/text-generation-webui/blob/main/instruction-templates/Vicuna-v1.1.yaml + "{%- 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'] + '\n' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{-'ASSISTANT:'-}}{%- endif -%}", + // 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 + "{%- 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'] + '\n' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{-'ASSISTANT:'-}}{%- endif -%}" }; std::vector expected_output = { // teknium/OpenHermes-2.5-Mistral-7B @@ -52,7 +58,11 @@ int main(void) { // OrionStarAI/Orion-14B-Chat "Human: You are a helpful assistant\n\nHello\n\nAssistant: Hi thereHuman: Who are you\n\nAssistant: I am an assistant Human: Another question\n\nAssistant: ", // openchat/openchat-3.5-0106 - "You are a helpful assistant<|end_of_turn|>GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi there<|end_of_turn|>GPT4 Correct User: Who are you?<|end_of_turn|>GPT4 Correct Assistant: I am an assistant <|end_of_turn|>GPT4 Correct User: Another question<|end_of_turn|>GPT4 Correct Assistant:" + "You are a helpful assistant<|end_of_turn|>GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi there<|end_of_turn|>GPT4 Correct User: Who are you<|end_of_turn|>GPT4 Correct Assistant: I am an assistant <|end_of_turn|>GPT4 Correct User: Another question<|end_of_turn|>GPT4 Correct Assistant:", + // eachadea/vicuna-13b-1.1 + "You are a helpful assistant\n\nUSER: Hello\nASSISTANT: Hi there\nUSER: Who are you\nASSISTANT: I am an assistant \nUSER: Another question\nASSISTANT:", + // Orca-Vicuna + "SYSTEM: You are a helpful assistant\nUSER: Hello\nASSISTANT: Hi there\nUSER: Who are you\nASSISTANT: I am an assistant \nUSER: Another question\nASSISTANT:" }; std::vector formatted_chat(1024); int32_t res;