From 9debd64cef2e1e24b6dd8c944d349b6ec58a3942 Mon Sep 17 00:00:00 2001
From: hiyouga <hiyouga@buaa.edu.cn>
Date: Tue, 6 Feb 2024 14:57:23 +0800
Subject: [PATCH] add models

Former-commit-id: 85622ae757e2ffe7f3da15f0a9123e8410d82b28
---
 src/llmtuner/data/template.py    |  3 ++-
 src/llmtuner/extras/constants.py | 33 ++++++++++++++------------------
 2 files changed, 16 insertions(+), 20 deletions(-)

diff --git a/src/llmtuner/data/template.py b/src/llmtuner/data/template.py
index 03f67a5b..cf4c6d53 100644
--- a/src/llmtuner/data/template.py
+++ b/src/llmtuner/data/template.py
@@ -376,7 +376,8 @@ register_template(
 
 register_template(
     name="deepseekcoder",
-    format_user=StringFormatter(slots=["### Instruction:\n{{content}}\n### Response:\n"]),
+    format_user=StringFormatter(slots=["### Instruction:\n{{content}}\n### Response:"]),
+    format_assistant=StringFormatter(slots=["\n", "{{content}}"]),
     format_separator=EmptyFormatter(slots=["\n", {"token": "<|EOT|>"}, "\n"]),
     default_system=(
         "You are an AI programming assistant, utilizing the Deepseek Coder model, "
diff --git a/src/llmtuner/extras/constants.py b/src/llmtuner/extras/constants.py
index 73a90a84..cfa69730 100644
--- a/src/llmtuner/extras/constants.py
+++ b/src/llmtuner/extras/constants.py
@@ -219,22 +219,32 @@ register_model_group(
 
 register_model_group(
     models={
-        "DeepSeekLLM-7B-Base": {
+        "DeepSeek-LLM-7B-Base": {
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-7b-base",
             DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-7b-base",
         },
-        "DeepSeekLLM-67B-Base": {
+        "DeepSeek-LLM-67B-Base": {
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-67b-base",
             DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-67b-base",
         },
-        "DeepSeekLLM-7B-Chat": {
+        "DeepSeek-LLM-7B-Chat": {
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-7b-chat",
             DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-7b-chat",
         },
-        "DeepSeekLLM-67B-Chat": {
+        "DeepSeek-LLM-67B-Chat": {
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-67b-chat",
             DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-67b-chat",
         },
+        "DeepSeek-Math-7B-Base": {DownloadSource.DEFAULT: "deepseek-ai/deepseek-math-7b-base"},
+        "DeepSeek-Math-7B-Chat": {DownloadSource.DEFAULT: "deepseek-ai/deepseek-math-7b-instruct"},
+        "DeepSeek-MoE-16B-Base": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-base",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-base",
+        },
+        "DeepSeek-MoE-16B-Chat": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat",
+        },
     },
     template="deepseek",
 )
@@ -265,21 +275,6 @@ register_model_group(
 )
 
 
-register_model_group(
-    models={
-        "DeepSeekMoE-16B-Base": {
-            DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-base",
-            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-base",
-        },
-        "DeepSeekMoE-16B-Chat": {
-            DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat",
-            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat",
-        },
-    },
-    template="deepseek",
-)
-
-
 register_model_group(
     models={
         "Falcon-7B": {