Update chat template
Browse files- tokenizer_config.json +2 -2
tokenizer_config.json
CHANGED
@@ -169,7 +169,7 @@
|
|
169 |
]
|
170 |
},
|
171 |
"bos_token": "<s>",
|
172 |
-
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content']
|
173 |
"clean_up_tokenization_spaces": false,
|
174 |
"eos_token": "</s>",
|
175 |
"extra_special_tokens": {},
|
@@ -177,4 +177,4 @@
|
|
177 |
"pad_token": "</s>",
|
178 |
"tokenizer_class": "InternLM2Tokenizer",
|
179 |
"unk_token": "<unk>"
|
180 |
-
}
|
|
|
169 |
]
|
170 |
},
|
171 |
"bos_token": "<s>",
|
172 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}\n {%- if message['role'] == 'user' and template -%}\n {{- '<|im_start|>' + message['role'] -}}\n {{ '\n# Template:' }}\n {{- '\n' + template }}\n {% if examples %}\n {{- '# Examples:' }}\n {% for example in examples %}\n {{- '## Input:\n' }}\n {{- example['input'] + '\n' }}\n {{- '## Output:\n' }}\n {{- example['output'] | trim }}\n {% endfor %}\n {%- endif %}\n {{- '# Context:' }}\n {% if message['content'] is string %}\n {{- message['content'] | trim }}\n {% else %}\n {% for content in message['content'] %}\n {%- if content is string %}\n {{- content | trim }}\n {%- elif content['type'] == 'text' %}\n {{- content['text'] | trim }}\n {%- endif %}\n {% endfor %}\n {% endif %}\n {{- '<|im_end|> '}}\n {% else %}\n {{- '<|im_start|>' + message['role'] }}\n {% if message['content'] is string %}\n {{- message['content'] | trim }}\n {% else %}\n {% for content in message['content'] %}\n {%- if content is string %}\n {{- content | trim }}\n {%- elif content['type'] == 'text' %}\n {{- content['text'] | trim }}\n {%- endif %}\n {% endfor %}\n {% endif %}\n {{- '<|im_end|> '}}\n {% endif %}\n{% endfor -%}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant' }}\n{% endif -%}\n",
|
173 |
"clean_up_tokenization_spaces": false,
|
174 |
"eos_token": "</s>",
|
175 |
"extra_special_tokens": {},
|
|
|
177 |
"pad_token": "</s>",
|
178 |
"tokenizer_class": "InternLM2Tokenizer",
|
179 |
"unk_token": "<unk>"
|
180 |
+
}
|