Remove alpaca, match deepseek with jinja output

llama.cpp

@@ -15733,22 +15733,19 @@ static int32_t llama_chat_apply_template_internal(
         if (add_ass) {
             ss << "ASSISTANT:";
         }
-    } else if (tmpl == "alpaca" || tmpl.find("### Instruction:\\n") != std::string::npos) {
+    } else if (tmpl == "deepseek" || (tmpl.find("### Instruction:") != std::string::npos && tmpl.find("<|EOT|>") != std::string::npos)) {
-        // wxjiao/alpaca-7b, deepseek-ai/deepseek-coder-33b-instruct
+        // deepseek-ai/deepseek-coder-33b-instruct
+        // Use of both U+ff5c and U+007c pipes is deliberate, based on the Jinja template
         for (auto message : chat) {
             std::string role(message->role);
             if (role == "system") {
-                ss << message->content << "\n\n";
+                ss << "<｜begin▁of▁sentence｜>" << message->content;
             } else if (role == "user") {
-                ss << "### Instruction:\n" << message->content << "\n\n";
+                ss << "### Instruction:\n" << message->content << "\n";
             } else if (role == "assistant") {
-                ss << "### Response:\n" << message->content << "\n\n";
+                ss << "### Response:\n" << message->content << "\n<|EOT|>\n";
             }
         }
-        if (add_ass) {
-            ss << "### Response:\n";
-        }
-
     } else {
         // template not supported
         return -1;

tests/test-chat-template.cpp

@@ -41,8 +41,7 @@ int main(void) {
         // 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 -%}",
-        // wxjiao/alpaca-7b, deepseek-ai/deepseek-coder-33b-instruct
+        // 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 = {
@@ -66,8 +65,8 @@ 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:",
-        // wxjiao/alpaca-7b, deepseek-ai/deepseek-coder-33b-instruct
+        // 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",
+        "<｜begin▁of▁sentence｜>You are a helpful assistant### Instruction:\nHello\n### Response:\nHi there\n<|EOT|>\n### Instruction:\nWho are you\n### Response:\n   I am an assistant   \n<|EOT|>\n### Instruction:\nAnother question\n"
     };
     std::vector<char> formatted_chat(1024);
     int32_t res;