From 733cb9087b4ba9eb60aeafb3a47bd1cddec9f790 Mon Sep 17 00:00:00 2001
From: moontidef <53668275+relic-yuexi@users.noreply.github.com>
Date: Mon, 5 Aug 2024 23:55:45 +0800
Subject: [PATCH] fix: fix the deepseekcoder template to avoid repeat problem

Former-commit-id: b82ecbedd0fecd85195217916cba3c21998bd10b
---
 src/llamafactory/data/template.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/src/llamafactory/data/template.py b/src/llamafactory/data/template.py
index db0393d1..0ec95f33 100644
--- a/src/llamafactory/data/template.py
+++ b/src/llamafactory/data/template.py
@@ -586,8 +586,7 @@ _register_template(
 _register_template(
     name="deepseekcoder",
     format_user=StringFormatter(slots=["### Instruction:\n{{content}}\n### Response:"]),
-    format_assistant=StringFormatter(slots=["\n{{content}}\n"]),
-    format_separator=EmptyFormatter(slots=["\n"]),
+    format_assistant=StringFormatter(slots=["{{content}}\n<|EOT|>"]),
     format_prefix=EmptyFormatter(slots=[{"bos_token"}]),
     default_system=(
         "You are an AI programming assistant, utilizing the Deepseek Coder model, "
@@ -595,6 +594,8 @@ _register_template(
         "For politically sensitive questions, security and privacy issues, "
         "and other non-computer science questions, you will refuse to answer\n"
     ),
+    stop_words=["<|EOT|>"],
+    replace_eos=True,
 )