diff --git a/src/llama.cpp b/src/llama.cpp
index b97b5e2795c0d..c879c3d5c15e4 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -19559,6 +19559,21 @@ static int32_t llama_chat_apply_template_internal(
         if (add_ass) {
             ss << "ASSISTANT:";
         }
+    } else if (tmpl == "alpaca" || (tmpl.find("### Instruction:") != std::string::npos && tmpl.find("<|EOT|>") == std::string::npos)) {
+        // meta-math/MetaMath-7B-V1.0
+        for (auto message : chat) {
+            std::string role(message->role);
+            if (role == "system") {
+                ss << message->content << "\n\n";
+            } else if (role == "user") {
+                ss << "### Instruction:\n" << message->content << "\n\n";
+            } else if (role == "assistant") {
+                ss << "### Response:\n" << message->content << "\n\n";
+            }
+        }
+        if (add_ass) {
+            ss << "### Response:\n";
+        }
     } else if (tmpl == "deepseek" || (tmpl.find("### Instruction:") != std::string::npos && tmpl.find("<|EOT|>") != std::string::npos)) {
         // deepseek-ai/deepseek-coder-33b-instruct
         for (auto message : chat) {
diff --git a/tests/test-chat-template.cpp b/tests/test-chat-template.cpp
index d19ba8633e8c2..c0f84132b163f 100644
--- a/tests/test-chat-template.cpp
+++ b/tests/test-chat-template.cpp
@@ -46,6 +46,9 @@ 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 -%}",
+        // meta-math/MetaMath-7B-V1.0
+        // No template included in tokenizer_config.json, so this template likely needs to be manually set.
+        "{%- set ns = namespace(found=false) -%} {%- for message in messages -%} {%- if message['role'] == 'system' -%} {%- set ns.found = true -%} {%- endif -%} {%- endfor -%} {%- if not ns.found -%} {{- '' + 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' + '\n\n' -}} {%- endif %} {%- for message in messages %} {%- if message['role'] == 'system' -%} {{- '' + message['content'] + '\n\n' -}} {%- else -%} {%- if message['role'] == 'user' -%} {{-'### Instruction:\n' + message['content'] + '\n\n'-}} {%- else -%} {{-'### Response:\n' + message['content'] + '\n\n' -}} {%- endif -%} {%- endif -%} {%- endfor -%} {%- if add_generation_prompt -%} {{-'### Response:\n'-}} {%- 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 %}",
         // Llama-3
@@ -82,6 +85,8 @@ 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:",
+        // meta-math/MetaMath-7B-V1.0
+        "You are a helpful assistant\n\n### Instruction:\nHello\n\n### Response:\nHi there\n\n### Instruction:\nWho are you\n\n### Response:\n   I am an assistant   \n\n### Instruction:\nAnother question\n\n### Response:\n",
         // 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|>",
         // Llama 3