diff --git a/models/templates/ibm-granite-granite-4.0.jinja b/models/templates/ibm-granite-granite-4.0.jinja new file mode 100644 index 0000000000..82e3ebf57b --- /dev/null +++ b/models/templates/ibm-granite-granite-4.0.jinja @@ -0,0 +1,118 @@ +{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n' %} +{%- set tools_system_message_suffix = '\n\n\nFor each tool call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %} +{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within XML tags:\n' %} +{%- set documents_system_message_suffix = '\n\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %} +{%- set g4_default_system_message = 'You are a helpful assistant. Please ensure responses are professional, accurate, and safe.' %} +{%- if available_tools is defined and available_tools %} + {%- set tools = available_tools %} +{%- endif %} +{%- set ns = namespace(tools_system_message=tools_system_message_prefix, + documents_system_message=documents_system_message_prefix, + default_system_message=g4_default_system_message, + system_message='' + ) %} +{%- if tools %} + {%- for tool in tools %} + {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %} + {%- endfor %} + {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %} +{%- else %} + {%- set ns.tools_system_message = '' %} +{%- endif %} +{%- if documents %} + {%- for document in documents %} + {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %} + {%- endfor %} + {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %} +{%- else %} + {%- set ns.documents_system_message = '' %} +{%- endif %} +{%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {%- set ns.system_message = messages[0].content %} + {%- elif messages[0].content is iterable %} + {%- for entry in messages[0].content %} + {%- if entry.type== 'text' %} + {%- if ns.system_message != '' %} + {%- set ns.system_message = ns.system_message + '\n' %} + {%- endif %} + {%- set ns.system_message = ns.system_message + entry.text %} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if tools and documents %} + {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %} + {%- elif tools %} + {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %} + {%- elif documents %} + {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %} + {%- endif %} +{%- else %} + {%- if tools and documents %} + {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %} + {%- elif tools %} + {%- set ns.system_message = ns.tools_system_message %} + {%- elif documents %} + {%- set ns.system_message = ns.documents_system_message %} + {%- endif %} +{%- endif %} +{%- if ns.system_message %} + {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }} +{%- else %} + {{- '<|start_of_role|>system<|end_of_role|>' + ns.default_system_message + '<|end_of_text|>\n' }} +{%- endif %} +{%- for message in messages %} + {%- set content = namespace(val='') %} + {%- if message.content is string %} + {%- set content.val = message.content %} + {%- else %} + {%- if message.content is iterable %} + {%- for entry in message.content %} + {%- if entry.type== 'text' %} + {%- if content.val != '' %} + {%- set content.val = content.val + '\n' %} + {%- endif %} + {%- set content.val = content.val + entry.text %} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- endif %} + {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %} + {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }} + {%- elif message.role == 'assistant' %} + {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content.val) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|end_of_text|>\n' }} + {%- elif message.role == 'tool' %} + {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %} + {{- '<|start_of_role|>user<|end_of_role|>' }} + {%- endif %} + {{- '\n\n' }} + {{- content.val }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %} + {{- '<|end_of_text|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_of_role|>assistant<|end_of_role|>' }} +{%- endif %} \ No newline at end of file diff --git a/src/llama-chat.cpp b/src/llama-chat.cpp index 78cbc38dbb..80a88fadec 100644 --- a/src/llama-chat.cpp +++ b/src/llama-chat.cpp @@ -60,7 +60,8 @@ static const std::map LLM_CHAT_TEMPLATES = { { "exaone4", LLM_CHAT_TEMPLATE_EXAONE_4 }, { "exaone-moe", LLM_CHAT_TEMPLATE_EXAONE_MOE }, { "rwkv-world", LLM_CHAT_TEMPLATE_RWKV_WORLD }, - { "granite", LLM_CHAT_TEMPLATE_GRANITE }, + { "granite", LLM_CHAT_TEMPLATE_GRANITE_3_X }, + { "granite-4.0", LLM_CHAT_TEMPLATE_GRANITE_4_0 }, { "gigachat", LLM_CHAT_TEMPLATE_GIGACHAT }, { "megrez", LLM_CHAT_TEMPLATE_MEGREZ }, { "yandex", LLM_CHAT_TEMPLATE_YANDEX }, @@ -191,7 +192,10 @@ llm_chat_template llm_chat_detect_template(const std::string & tmpl) { } else if (tmpl_contains("rwkv-world") || tmpl_contains("{{- 'User: ' + message['content']|trim + '\\n\\n' -}}")) { return LLM_CHAT_TEMPLATE_RWKV_WORLD; } else if (tmpl_contains("<|start_of_role|>")) { - return LLM_CHAT_TEMPLATE_GRANITE; + if (tmpl_contains("") || tmpl_contains("")) { + return LLM_CHAT_TEMPLATE_GRANITE_4_0; + } + return LLM_CHAT_TEMPLATE_GRANITE_3_X; } else if (tmpl_contains("message['role'] + additional_special_tokens[0] + message['content'] + additional_special_tokens[1]")) { return LLM_CHAT_TEMPLATE_GIGACHAT; } else if (tmpl_contains("<|role_start|>")) { @@ -617,8 +621,8 @@ int32_t llm_chat_apply_template( ss << "Assistant: " << trim(chat[i]->content) << "\n\n"; } } - } else if (tmpl == LLM_CHAT_TEMPLATE_GRANITE) { - // IBM Granite template + } else if (tmpl == LLM_CHAT_TEMPLATE_GRANITE_3_X) { + // IBM Granite 3.x template for (const auto & message : chat) { std::string role(message->role); ss << "<|start_of_role|>" << role << "<|end_of_role|>"; @@ -630,6 +634,20 @@ int32_t llm_chat_apply_template( if (add_ass) { ss << "<|start_of_role|>assistant<|end_of_role|>"; } + } else if (tmpl == LLM_CHAT_TEMPLATE_GRANITE_4_0) { + // IBM Granite 4.0 template + for (const auto & message : chat) { + std::string role(message->role); + if (role == "assistant_tool_call") { + ss << "<|start_of_role|>assistant<|end_of_role|><|tool_call|>"; + } else { + ss << "<|start_of_role|>" << role << "<|end_of_role|>"; + } + ss << message->content << "<|end_of_text|>\n"; + } + if (add_ass) { + ss << "<|start_of_role|>assistant<|end_of_role|>"; + } } else if (tmpl == LLM_CHAT_TEMPLATE_GIGACHAT) { // GigaChat template bool has_system = !chat.empty() && std::string(chat[0]->role) == "system"; diff --git a/src/llama-chat.h b/src/llama-chat.h index ef7dfecebd..2542f3cc86 100644 --- a/src/llama-chat.h +++ b/src/llama-chat.h @@ -39,7 +39,8 @@ enum llm_chat_template { LLM_CHAT_TEMPLATE_EXAONE_4, LLM_CHAT_TEMPLATE_EXAONE_MOE, LLM_CHAT_TEMPLATE_RWKV_WORLD, - LLM_CHAT_TEMPLATE_GRANITE, + LLM_CHAT_TEMPLATE_GRANITE_3_X, + LLM_CHAT_TEMPLATE_GRANITE_4_0, LLM_CHAT_TEMPLATE_GIGACHAT, LLM_CHAT_TEMPLATE_MEGREZ, LLM_CHAT_TEMPLATE_YANDEX, diff --git a/tests/test-chat-template.cpp b/tests/test-chat-template.cpp index 6cc132131c..bf45d737c8 100644 --- a/tests/test-chat-template.cpp +++ b/tests/test-chat-template.cpp @@ -354,6 +354,7 @@ int main_automated_tests(void) { std::string bos_token = ""; std::string eos_token = ""; bool supported_with_jinja = true; + std::vector extra_conversation = {}; }; std::vector test_cases { { @@ -604,6 +605,26 @@ int main_automated_tests(void) { /* .expected_output_jinja= */ "system\nYou are a helpful assistantuser\nHelloassistant\nHi thereuser\nWho are youassistant\nI am an assistantuser\nAnother questionassistant\n", /* .bos_token= */ "", /* .eos_token= */ "", + }, + { + /* .name= */ "ibm-granite/granite-3.x (tool call)", + /* .template_str= */ "{%- for message in messages %}\n {%- if message['role'] == 'assistant_tool_call' %}\n {{- '<|start_of_role|>assistant<|end_of_role|><|tool_call|>' + message['content'] + '<|end_of_text|>\\n' }}\n {%- else %}\n {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\\n' }}\n {%- endif %}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' }}\n {%- endif %}\n{%- endfor %}", + /* .expected_output= */ "<|start_of_role|>system<|end_of_role|>You are a helpful assistant<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Hello<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>Hi there<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Who are you<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|> I am an assistant <|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Another question<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>What is the weather?<|end_of_text|>\n<|start_of_role|>assistant_tool_call<|end_of_role|><|tool_call|>[{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}]<|end_of_text|>\n<|start_of_role|>tool_response<|end_of_role|>{\"temperature\": 72}<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>", + /* .expected_output_jinja= */ "<|start_of_role|>system<|end_of_role|>You are a helpful assistant<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Hello<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>Hi there<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Who are you<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|> I am an assistant <|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Another question<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>What is the weather?<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|><|tool_call|>[{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}]<|end_of_text|>\n<|start_of_role|>tool_response<|end_of_role|>{\"temperature\": 72}<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>", + /* .bos_token= */ "", + /* .eos_token= */ "", + /* .supported_with_jinja= */ true, + /* .extra_conversation= */ {{"user", "What is the weather?"}, {"assistant_tool_call", "[{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}]"}, {"tool_response", "{\"temperature\": 72}"}}, + }, + { + /* .name= */ "ibm-granite/granite-4.0 (tool call)", + /* .template_str= */ "{%- for message in messages %}\n {%- if message['role'] == 'assistant_tool_call' %}\n {{- '<|start_of_role|>assistant<|end_of_role|><|tool_call|>' + message['content'] + '<|end_of_text|>\\n' }}\n {%- else %}\n {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\\n' }}\n {%- endif %}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' }}\n {%- endif %}\n{%- endfor %}\n{# #}", + /* .expected_output= */ "<|start_of_role|>system<|end_of_role|>You are a helpful assistant<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Hello<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>Hi there<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Who are you<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|> I am an assistant <|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Another question<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>What is the weather?<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|><|tool_call|>\n{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}\n<|end_of_text|>\n<|start_of_role|>tool_response<|end_of_role|>{\"temperature\": 72}<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>", + /* .expected_output_jinja= */ "", + /* .bos_token= */ "", + /* .eos_token= */ "", + /* .supported_with_jinja= */ true, + /* .extra_conversation= */ {{"user", "What is the weather?"}, {"assistant_tool_call", "\n{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}\n"}, {"tool_response", "{\"temperature\": 72}"}}, } }; std::vector formatted_chat(1024); @@ -627,11 +648,13 @@ int main_automated_tests(void) { for (const auto & test_case : test_cases) { std::cout << "\n\n=== " << test_case.name << " ===\n\n"; - formatted_chat.resize(1024); + auto conv = conversation; + conv.insert(conv.end(), test_case.extra_conversation.begin(), test_case.extra_conversation.end()); + formatted_chat.resize(2048); res = llama_chat_apply_template( test_case.template_str.c_str(), - conversation.data(), - conversation.size(), + conv.data(), + conv.size(), add_generation_prompt, formatted_chat.data(), formatted_chat.size() @@ -658,11 +681,15 @@ int main_automated_tests(void) { } std::cout << "\n\n=== " << test_case.name << " (jinja) ===\n\n"; try { + auto msgs = messages; + for (const auto & msg : test_case.extra_conversation) { + msgs.push_back(simple_msg(msg.role, msg.content)); + } auto output = format_using_common( test_case.template_str, test_case.bos_token, test_case.eos_token, - messages); + msgs); auto expected_output = normalize_newlines(test_case.expected_output_jinja.empty() ? test_case.expected_output : test_case.expected_output_jinja); if (output != expected_output) { std::cout << "Template:```\n" << test_case.template_str << "\n```"; diff --git a/tests/test-chat.cpp b/tests/test-chat.cpp index b66916687b..5a90590b77 100644 --- a/tests/test-chat.cpp +++ b/tests/test-chat.cpp @@ -1929,6 +1929,22 @@ static void test_template_output_peg_parsers(bool detailed_debug) { // .run(); } + { + // IBM Granite 4.0 (production template shared by h-tiny, h-small, micro) + // Uses XML tags for tool calls, tools in system message + auto tst = peg_tester("models/templates/ibm-granite-granite-4.0.jinja", detailed_debug); + + tst.test("Hello, world!\nWhat's up?").expect(message_assist).run(); + + tst.test( + "\n" + "{\"name\": \"special_function\", \"arguments\": {\"arg1\": 1}}\n" + "") + .tools({ special_function_tool }) + .expect(message_assist_call) + .run(); + } + { // ByteDance-Seed-OSS (reasoning and tool calling model) auto tst = peg_tester("models/templates/ByteDance-Seed-OSS.jinja", detailed_debug);