From 5de45bf9899e8d4f43f4308a1140586f7475828e Mon Sep 17 00:00:00 2001
From: hiyouga <hiyouga@buaa.edu.cn>
Date: Thu, 16 Nov 2023 22:54:15 +0800
Subject: [PATCH] fix chatglm template

Former-commit-id: ed9f7705efbed0accf4dc5c9dfa9e3e7e15e1174
---
 src/llmtuner/data/template.py | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/src/llmtuner/data/template.py b/src/llmtuner/data/template.py
index 03b3c011..1bf24063 100644
--- a/src/llmtuner/data/template.py
+++ b/src/llmtuner/data/template.py
@@ -114,7 +114,7 @@ class Template:
             else:
                 prefix_ids = sep_ids + bos_ids
 
-            query_ids = self._convert_inputs_to_ids(tokenizer, context=self.prompt, query=query, idx=str(turn_idx))
+            query_ids = self._convert_inputs_to_ids(tokenizer, context=self.prompt, query=query, idx=str(turn_idx+1))
             resp_ids = self._convert_inputs_to_ids(tokenizer, context=[resp])
             encoded_pairs.append((prefix_ids + query_ids, resp_ids + eos_ids))
         return encoded_pairs
@@ -350,6 +350,8 @@ register_template(
     prefix=[
         {"token": "[gMASK]"},
         {"token": "sop"},
+        {"token": "<|system|>"},
+        "\n",
         "{{system}}"
     ],
     prompt=[
@@ -358,7 +360,10 @@ register_template(
         "{{query}}",
         {"token": "<|assistant|>"}
     ],
-    system="",
+    system=(
+        "You are ChatGLM3, a large language model trained by Zhipu.AI. "
+        "Follow the user's instructions carefully. Respond using markdown."
+    ),
     sep=[],
     stop_words=[
         "<|user|>",