From f1a3b12ceda2c3c212d73cdaa376cf6d1775986b Mon Sep 17 00:00:00 2001
From: Kai Zau <kaizau@users.noreply.github.com>
Date: Sat, 30 Mar 2024 19:04:49 +0900
Subject: [PATCH] Add chat template for alpaca

---
 llama.cpp                    | 16 ++++++++++++++++
 tests/test-chat-template.cpp |  9 +++++++--
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/llama.cpp b/llama.cpp
index 580a4e53b..7a694e2ba 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -15733,6 +15733,22 @@ static int32_t llama_chat_apply_template_internal(
         if (add_ass) {
             ss << "ASSISTANT:";
         }
+    } else if (tmpl == "alpaca" || tmpl.find("### Instruction:\\n") != std::string::npos) {
+        // wxjiao/alpaca-7b, deepseek-ai/deepseek-coder-33b-instruct
+        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 {
         // template not supported
         return -1;
diff --git a/tests/test-chat-template.cpp b/tests/test-chat-template.cpp
index 96b136908..ba1bc0fd8 100644
--- a/tests/test-chat-template.cpp
+++ b/tests/test-chat-template.cpp
@@ -40,7 +40,10 @@ int main(void) {
         "{%- for message in messages %}{%- if message['role'] == 'system' -%}{{- '' + message['content'] + '\n\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 -%}",
         // Orca-Vicuna
         // No template included in config_tokenizer.json; extracted from: https://github.com/oobabooga/text-generation-webui/blob/main/instruction-templates/Orca-Vicuna.yaml
-        "{%- 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 -%}"
+        "{%- 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 -%}",
+        // wxjiao/alpaca-7b, deepseek-ai/deepseek-coder-33b-instruct
+        // No original Alpaca template Jinja, so using DeepSeek's instead
+        "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}"
     };
     std::vector<std::string> expected_output = {
         // teknium/OpenHermes-2.5-Mistral-7B
@@ -62,7 +65,9 @@ int main(void) {
         // eachadea/vicuna-13b-1.1
         "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:"
+        "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:",
+        // wxjiao/alpaca-7b, deepseek-ai/deepseek-coder-33b-instruct
+        "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",
     };
     std::vector<char> formatted_chat(1024);
     int32_t res;