singhsidhukuldeep
commited on
Commit
•
05ca608
1
Parent(s):
cc5b7e0
Adding chat_template to tokenizer_config.json file
Browse filesI have tested the `chat_template`
It is from the official `mistralai/Mistral-Large-Instruct-2407`
Should solve this error: `Cannot use apply_chat_template() because tokenizer.chat_template is not set and no template argument was passed! For information about writing templates and setting the tokenizer.chat_template attribute, please see the documentation at https://huggingface.co/docs/transformers/main/en/chat_templating`
- tokenizer_config.json +2 -1
tokenizer_config.json
CHANGED
@@ -6173,6 +6173,7 @@
|
|
6173 |
}
|
6174 |
},
|
6175 |
"bos_token": "<s>",
|
|
|
6176 |
"clean_up_tokenization_spaces": false,
|
6177 |
"eos_token": "</s>",
|
6178 |
"legacy": true,
|
@@ -6183,4 +6184,4 @@
|
|
6183 |
"tokenizer_class": "LlamaTokenizer",
|
6184 |
"unk_token": "<unk>",
|
6185 |
"use_default_system_prompt": false
|
6186 |
-
}
|
|
|
6173 |
}
|
6174 |
},
|
6175 |
"bos_token": "<s>",
|
6176 |
+
"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",
|
6177 |
"clean_up_tokenization_spaces": false,
|
6178 |
"eos_token": "</s>",
|
6179 |
"legacy": true,
|
|
|
6184 |
"tokenizer_class": "LlamaTokenizer",
|
6185 |
"unk_token": "<unk>",
|
6186 |
"use_default_system_prompt": false
|
6187 |
+
}
|