Align tokenizer with mistral-common

README.md

@@ -6,12 +6,6 @@ license: apache-2.0
 
 ### 
 
-> [!IMPORTANT]
-> ❗ 
-> We recommend using `mistral_common` for tokenization as the transformers tokenizer has not been tested by the Mistral team and might give incorrect results.
-
----
-
 The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3.
 
 Mistral-7B-v0.3 has the following changes compared to [Mistral-7B-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2/edit/main/README.md)

tokenizer_config.json

@@ -6173,7 +6173,7 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{{bos_token}}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + '[/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.last and system_message is defined %}\n            {{- '[INST] ' + system_message + '\\n\\n' + message['content'] + '[/INST]' }}\n        {%- else %}\n            {{- '[INST] ' + message['content'] + '[/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,