Add Command R chat template (#6650)

* Add chat template for command-r model series

* Fix indentation

* Add chat template test for command-r models and update the implementation to trim whitespaces

* Remove debug print

diff --git a/llama.cpp b/llama.cpp
index b93c1abcd85d6f3a6986e11c5060c8506611b268..e3205e58cd64c242304b7d63db2dc1b366a1c669 100644 (file)
--- a/llama.cpp
+++ b/llama.cpp
@@ -16625,6 +16625,21 @@ static int32_t llama_chat_apply_template_internal(
         if (add_ass) {
             ss << "### Response:\n";
         }
+    } else if (tmpl == "command-r" || (tmpl.find("<|START_OF_TURN_TOKEN|>") != std::string::npos && tmpl.find("<|USER_TOKEN|>") != std::string::npos)) {
+        // CohereForAI/c4ai-command-r-plus
+        for (auto message : chat) {
+            std::string role(message->role);
+            if (role == "system") {
+                ss << "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>" << trim(message->content) << "<|END_OF_TURN_TOKEN|>";
+            } else if (role == "user") {
+                ss << "<|START_OF_TURN_TOKEN|><|USER_TOKEN|>" << trim(message->content) << "<|END_OF_TURN_TOKEN|>";
+            } else if (role == "assistant") {
+                ss << "<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>" << trim(message->content) << "<|END_OF_TURN_TOKEN|>";
+            }
+        }
+        if (add_ass) {
+            ss << "<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>";
+        }
     } else {
         // template not supported
         return -1;

diff --git a/tests/test-chat-template.cpp b/tests/test-chat-template.cpp
index 73c3536fdb878b1ea0b6489cbe672aec7862ffe7..522cc7d0d9e8488b76aa720802b685ef6966ef7c 100644 (file)
--- a/tests/test-chat-template.cpp
+++ b/tests/test-chat-template.cpp
@@ -45,6 +45,8 @@ int main(void) {
         // Orca-Vicuna
         // No template included in tokenizer_config.json, so this template likely needs to be manually set.
         "{%- 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 -%}",
+        // CohereForAI/c4ai-command-r-plus
+        "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% 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 %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
     };
     std::vector<std::string> expected_output = {
         // teknium/OpenHermes-2.5-Mistral-7B
@@ -69,6 +71,8 @@ int main(void) {
         "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
         "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:",
+        // CohereForAI/c4ai-command-r-plus
+        "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>You are a helpful assistant<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>Hi there<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Who are you<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>I am an assistant<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Another question<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>",
     };
     std::vector<char> formatted_chat(1024);
     int32_t res;