Align tokenizer_config chat template with docs.mistral.ai chat template
Browse filesAs others mentioned, there is a subtle difference between chat templates:
[https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1/discussions/53](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1/discussions/53)
This edit aligns with:
[https://docs.mistral.ai/llm/mistral-instruct-v0.1#chat-template](https://docs.mistral.ai/llm/mistral-instruct-v0.1#chat-template)
[https://docs.mistral.ai/usage/guardrailing#appendix](https://docs.mistral.ai/usage/guardrailing#appendix)
If accepted, model card should be modified accordingly.
- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
@@ -29,7 +29,7 @@
|
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
"bos_token": "<s>",
|
32 |
-
"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
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": true,
|
|
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
"bos_token": "<s>",
|
32 |
+
"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 %}",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": true,
|