chat : add Granite 4.1 chat template (#23518)

diff --git a/models/templates/ibm-granite-granite-4.1.jinja b/models/templates/ibm-granite-granite-4.1.jinja
new file mode 100644 (file)
index 0000000..903cac6
--- /dev/null
+++ b/models/templates/ibm-granite-granite-4.1.jinja
@@ -0,0 +1,114 @@
+{%- 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 <tools></tools> XML tags:\n<tools>'  %}
+{%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. 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 <documents></documents> XML tags:\n<documents>' %}
+{%- set documents_system_message_suffix = '\n</documents>\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.' %}
+{%- 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,
+                       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' }}
+{%- 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 %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- 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<tool_response>\n' }}
+        {{- content.val }}
+        {{- '\n</tool_response>' }}
+        {%- 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 f10397747b0ee82b11f521d2f3e184ed3cd7eacc..6d822ec62d6bac7576bc537fbca55721dccaf293 100644 (file)
--- a/src/llama-chat.cpp
+++ b/src/llama-chat.cpp
@@ -62,6 +62,7 @@ static const std::map<std::string, llm_chat_template> LLM_CHAT_TEMPLATES = {
     { "rwkv-world",        LLM_CHAT_TEMPLATE_RWKV_WORLD        },
     { "granite",           LLM_CHAT_TEMPLATE_GRANITE_3_X       },
     { "granite-4.0",       LLM_CHAT_TEMPLATE_GRANITE_4_0       },
+    { "granite-4.1",       LLM_CHAT_TEMPLATE_GRANITE_4_1       },
     { "gigachat",          LLM_CHAT_TEMPLATE_GIGACHAT          },
     { "megrez",            LLM_CHAT_TEMPLATE_MEGREZ            },
     { "yandex",            LLM_CHAT_TEMPLATE_YANDEX            },
@@ -194,7 +195,10 @@ llm_chat_template llm_chat_detect_template(const std::string & tmpl) {
         return LLM_CHAT_TEMPLATE_RWKV_WORLD;
     } else if (tmpl_contains("<|start_of_role|>")) {
         if (tmpl_contains("<tool_call>") || tmpl_contains("<tools>")) {
-            return LLM_CHAT_TEMPLATE_GRANITE_4_0;
+            if (tmpl_contains("g4_default_system_message")) {
+                return LLM_CHAT_TEMPLATE_GRANITE_4_0;
+            }
+            return LLM_CHAT_TEMPLATE_GRANITE_4_1;
         }
         return LLM_CHAT_TEMPLATE_GRANITE_3_X;
     } else if (tmpl_contains("message['role'] + additional_special_tokens[0] + message['content'] + additional_special_tokens[1]")) {
@@ -651,6 +655,20 @@ 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_1) {
+        // IBM Granite 4.1 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 ea6540c0be734cde9e93e505825912d5122c670a..dc37f919a9680b0887b3aaedef528a6f24ad7237 100644 (file)
--- a/src/llama-chat.h
+++ b/src/llama-chat.h
@@ -41,6 +41,7 @@ enum llm_chat_template {
     LLM_CHAT_TEMPLATE_RWKV_WORLD,
     LLM_CHAT_TEMPLATE_GRANITE_3_X,
     LLM_CHAT_TEMPLATE_GRANITE_4_0,
+    LLM_CHAT_TEMPLATE_GRANITE_4_1,
     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 bf45d737c83207f2e92978a7554d81ff97f1c342..c388dee1c4535869910e4d551bc66d8f76f4a39d 100644 (file)
--- a/tests/test-chat-template.cpp
+++ b/tests/test-chat-template.cpp
@@ -618,6 +618,16 @@ int main_automated_tests(void) {
         },
         {
             /* .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{# <tool_call> <tools> g4_default_system_message #}",
+            /* .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|><tool_call>\n{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}\n</tool_call><|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", "<tool_call>\n{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}\n</tool_call>"}, {"tool_response", "{\"temperature\": 72}"}},
+        },
+        {
+            /* .name= */ "ibm-granite/granite-4.1 (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{# <tool_call> <tools> #}",
             /* .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|><tool_call>\n{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}\n</tool_call><|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= */ "",

diff --git a/tests/test-chat.cpp b/tests/test-chat.cpp
index 1a5161cc101fc8f1e0c89ce5e7e7b7d7dc5a8d3b..30ea2c07213ca624774bebd3bbb2ab7d278e8eb7 100644 (file)
--- a/tests/test-chat.cpp
+++ b/tests/test-chat.cpp
@@ -2914,6 +2914,21 @@ static void test_template_output_peg_parsers(bool detailed_debug) {
             .run();
     }
 
+    {
+        // IBM Granite 4.1 (same format as 4.0)
+        auto tst = peg_tester("models/templates/ibm-granite-granite-4.1.jinja", detailed_debug);
+
+        tst.test("Hello, world!\nWhat's up?").expect(message_assist).run();
+
+        tst.test(
+               "<tool_call>\n"
+               "{\"name\": \"special_function\", \"arguments\": {\"arg1\": 1}}\n"
+               "</tool_call>")
+            .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);