Add `chat_template` in tokenizer config (#11)
Browse files- Add `chat_template` in tokenizer config (91b6fa1f5405def06916c6dd8f736a16a882cd2c)
Co-authored-by: Junlin Zhou <jlzhou@users.noreply.huggingface.co>
- tokenizer_config.json +1 -0
tokenizer_config.json
CHANGED
@@ -37,6 +37,7 @@
|
|
37 |
},
|
38 |
"additional_special_tokens": [],
|
39 |
"bos_token": "<s>",
|
|
|
40 |
"clean_up_tokenization_spaces": false,
|
41 |
"eos_token": "<|im_end|>",
|
42 |
"legacy": true,
|
|
|
37 |
},
|
38 |
"additional_special_tokens": [],
|
39 |
"bos_token": "<s>",
|
40 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|im_start|>user\n' + message['content'] + '<|im_end|>' }}\n{% elif message['role'] == 'system' %}\n{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>' }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|im_start|>assistant\n' + message['content'] + '<|im_end|>' }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|im_start|>assistant' }}\n{% endif %}\n{% endfor %}",
|
41 |
"clean_up_tokenization_spaces": false,
|
42 |
"eos_token": "<|im_end|>",
|
43 |
"legacy": true,
|