From 84367b9fd1f0aa5db1a1b80d14febe18e1e19a82 Mon Sep 17 00:00:00 2001
From: HanishKVC <hanishkvc@gmail.com>
Date: Tue, 23 Apr 2024 12:46:40 +0530
Subject: [PATCH] ChatON: Add template for DeepSeek

Was looking at the tokenized vector, and noticed that the EOS
mentioned by existing chat_apply_template of llama.cpp, is different
from what I noticed in tokenizer_config.json of deepseek llm, so
I have added two entries

* "deepseek-alt" which matches llama.cpp's chat_apply_template and
* "deepseek" which matches that in tokenizer_config.json.

This impacts the assistant suffix and reverse prompt entries.

CasOfThis: Need to look into other entries which I added previously
at a later time. However as the default logic should be picking the
EOS from model file, so I assume reverse-prompt being outofsync,
may not matter beyond a limit, potentially.
---
 common/chaton.hpp         |  3 +++
 examples/chaton_meta.json | 40 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+)

diff --git a/common/chaton.hpp b/common/chaton.hpp
index be9957ff9..222c8657f 100644
--- a/common/chaton.hpp
+++ b/common/chaton.hpp
@@ -49,6 +49,9 @@
  *   in-prefix, in-suffix and antiprompt of main.
  * These always adds any role specific prefix and suffix around the passed message.
  *
+ * Sample chaton_meta.json includes template info for
+ * * llama2, llama3, gemma, chatml, zephyr, deepseek
+ *
  */
 
 #include <string>
diff --git a/examples/chaton_meta.json b/examples/chaton_meta.json
index 05ffcc8fb..4f6bcfc30 100644
--- a/examples/chaton_meta.json
+++ b/examples/chaton_meta.json
@@ -99,6 +99,46 @@
 		},
 		"reverse-prompt": "<eos>",
 		"systemuser-1st-user-has-prefix": true
+	},
+	"deepseek-alt": {
+		"global": {
+			"begin": "",
+			"end": ""
+		},
+		"system": {
+			"prefix": "",
+			"suffix": "\n"
+		},
+		"user": {
+			"prefix": "### Instruction:\n",
+			"suffix": "\n"
+		},
+		"assistant": {
+			"prefix": "### Response:\n",
+			"suffix": "\n<|EOT|>\n"
+		},
+		"reverse-prompt": "<|EOT|>",
+		"systemuser-1st-user-has-prefix": true
+	},
+	"deepseek": {
+		"global": {
+			"begin": "",
+			"end": ""
+		},
+		"system": {
+			"prefix": "",
+			"suffix": "\n\n"
+		},
+		"user": {
+			"prefix": "User: ",
+			"suffix": "\n\n"
+		},
+		"assistant": {
+			"prefix": "Assistant: ",
+			"suffix": " <｜end▁of▁sentence｜>\n"
+		},
+		"reverse-prompt": "<｜end▁of▁sentence｜>",
+		"systemuser-1st-user-has-prefix": true
 	}
 }