Update README.md

README.md

@@ -10,6 +10,40 @@ model_type: mistral
 
 # Swallow-MS-7b-v0.1
 
+このモデルは[tokyotech-llm/Swallow-MS-7b-instruct-v0.1](https://huggingface.co/tokyotech-llm/Swallow-MS-7b-instruct-v0.1/commits/main)のtokenizer.chat_templateを以下に変更したものです。
+```
+tokenizer.chat_template = """{% if messages[0]['role'] == 'system' %}
+{% set loop_messages = messages[1:] %}
+{% set system_message = messages[0]['content'] %}
+{% elif false == true and not '<<SYS>>' in messages[0]['content'] %}
+{% set loop_messages = messages %}
+{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}
+{% else %}
+{% set loop_messages = messages %}
+{% set system_message = false %}
+{% endif %}
+{{ bos_token }}
+{% for message in loop_messages %}
+{% if (message['role'] == 'user') != ((loop.index0 + messages[0]['role'] == 'assistant') % 2 == 0) %}
+{{ raise_exception('Conversation roles must alternate starting from the first role.') }}
+{% endif %}
+{% if loop.index0 == 0 and system_message != false %}
+{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}
+{% else %}
+{% set content = message['content'] %}
+{% endif %}
+{% if message['role'] == 'user' %}
+{{ '[INST] ' + content.strip() + ' [/INST] ' }}
+{% elif message['role'] == 'system' %}
+{{ '<<SYS>>\n' + content.strip() + '\n<</SYS>>\n\n' }}
+{% elif message['role'] == 'assistant' %}
+{{ ''  + content.strip() + '' + eos_token }}
+{% endif %}
+{% endfor %}
+"""
+```
+元のモデルのrevisionは`8b17f1c87697fb354952fa0d1018568e50bdff56`です。
+
 Our Swallow-MS-7b-v0.1 model has undergone continual pre-training from the Mistral-7B-v0.1, primarily with the addition of Japanese language data. 
 
 # Model Release Updates