diff options
Diffstat (limited to 'tests/test-chat-template.cpp')
| -rw-r--r-- | tests/test-chat-template.cpp | 23 |
1 files changed, 15 insertions, 8 deletions
diff --git a/tests/test-chat-template.cpp b/tests/test-chat-template.cpp index 9830650d..d02b39e1 100644 --- a/tests/test-chat-template.cpp +++ b/tests/test-chat-template.cpp @@ -27,12 +27,20 @@ int main(void) { "{%- for idx in range(0, messages|length) -%}\\n{%- if messages[idx]['role'] == 'user' -%}\\n{%- if idx > 1 -%}\\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\\n{%- else -%}\\n{{- messages[idx]['content'] + ' [/INST]' -}}\\n{%- endif -%}\\n{% elif messages[idx]['role'] == 'system' %}\\n{{- '[INST] <<SYS>>\\\\n' + messages[idx]['content'] + '\\\\n<</SYS>>\\\\n\\\\n' -}}\\n{%- elif messages[idx]['role'] == 'assistant' -%}\\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\\n{% endif %}\\n{% endfor %}", // bofenghuang/vigogne-2-70b-chat "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif true == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'Vous êtes Vigogne, un assistant IA créé par Zaion Lab. Vous suivez extrêmement bien les instructions. Aidez autant que vous le pouvez.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% 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 %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\\\n' + system_message + '\\\\n<</SYS>>\\\\n\\\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\\\n' + content.strip() + '\\\\n<</SYS>>\\\\n\\\\n' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}", + // mlabonne/AlphaMonarch-7B + "{% for message in messages %}{{bos_token + message['role'] + '\\n' + message['content'] + eos_token + '\\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\\n' }}{% endif %}", }; - std::vector<std::string> expected_substr = { - "<|im_start|>assistant\n I am an assistant <|im_end|>\n<|im_start|>user\nAnother question<|im_end|>\n<|im_start|>assistant", - "[/INST]Hi there</s>[INST] Who are you [/INST] I am an assistant </s>[INST] Another question [/INST]", - "</s><s>[INST] Who are you [/INST] I am an assistant </s><s>[INST] Another question [/INST]", - "[/INST] Hi there </s>[INST] Who are you [/INST] I am an assistant </s>[INST] Another question [/INST]", + std::vector<std::string> expected_output = { + // teknium/OpenHermes-2.5-Mistral-7B + "<|im_start|>system\nYou are a helpful assistant<|im_end|>\n<|im_start|>user\nHello<|im_end|>\n<|im_start|>assistant\nHi there<|im_end|>\n<|im_start|>user\nWho are you<|im_end|>\n<|im_start|>assistant\n I am an assistant <|im_end|>\n<|im_start|>user\nAnother question<|im_end|>\n<|im_start|>assistant\n", + // mistralai/Mistral-7B-Instruct-v0.2 + "[INST] You are a helpful assistant\nHello [/INST]Hi there</s>[INST] Who are you [/INST] I am an assistant </s>[INST] Another question [/INST]", + // TheBloke/FusionNet_34Bx2_MoE-AWQ + "[INST] <<SYS>>\nYou are a helpful assistant\n<</SYS>>\n\nHello [/INST] Hi there </s><s>[INST] Who are you [/INST] I am an assistant </s><s>[INST] Another question [/INST]", + // bofenghuang/vigogne-2-70b-chat + "[INST] <<SYS>>\nYou are a helpful assistant\n<</SYS>>\n\nHello [/INST] Hi there </s>[INST] Who are you [/INST] I am an assistant </s>[INST] Another question [/INST]", + // mlabonne/AlphaMonarch-7B + "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", }; std::vector<char> formatted_chat(1024); int32_t res; @@ -43,7 +51,7 @@ int main(void) { for (size_t i = 0; i < templates.size(); i++) { std::string custom_template = templates[i]; - std::string substr = expected_substr[i]; + std::string expected = expected_output[i]; formatted_chat.resize(1024); res = llama_chat_apply_template( nullptr, @@ -57,8 +65,7 @@ int main(void) { formatted_chat.resize(res); std::string output(formatted_chat.data(), formatted_chat.size()); std::cout << output << "\n-------------------------\n"; - // expect the "formatted_chat" to contain pre-defined strings - assert(output.find(substr) != std::string::npos); + assert(output == expected); } return 0; } |