update tokenizer to include tool response format as well
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
@@ -151,7 +151,7 @@
|
|
151 |
"clean_up_tokenization_spaces": false,
|
152 |
"eos_token": "[EOS]",
|
153 |
"extra_special_tokens": {},
|
154 |
-
"chat_template": "{% if tools -%}\n {{ '<|im_system|>tool_declare<|im_middle|>' -}}\n {{- tools | tojson -}}\n {{ '<|im_end|>' -}}\n{%- endif -%}\n\n{%- for message in messages -%}\n {%- if loop.first and messages[0]['role'] != 'system' -%}\n {{ '<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>' }}\n {%- endif -%}\n {%- if message['role'] == 'system' -%}\n {{ '<|im_system|>system<|im_middle|>' }}\n {%- elif message['role'] == 'user' -%}\n {{ '<|im_user|>user<|im_middle|>' }}\n {%- elif message['role'] == 'assistant' -%}\n {{ '<|im_assistant|>assistant<|im_middle|>' }}\n {%- elif message['role'] == 'tool' -%}\n {{ '<|im_system|>tool<|im_middle|>' }}\n {%- endif -%}\n\n {%- if message['
|
155 |
"model_max_length": 1000000000000000019884624838656,
|
156 |
"pad_token": "[PAD]",
|
157 |
"tokenizer_class": "TikTokenTokenizer",
|
|
|
151 |
"clean_up_tokenization_spaces": false,
|
152 |
"eos_token": "[EOS]",
|
153 |
"extra_special_tokens": {},
|
154 |
+
"chat_template": "{% if tools -%}\n {{ '<|im_system|>tool_declare<|im_middle|>' -}}\n {{- tools | tojson -}}\n {{ '<|im_end|>' -}}\n{%- endif -%}\n\n{%- for message in messages -%}\n {%- if loop.first and messages[0]['role'] != 'system' -%}\n {{ '<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>' }}\n {%- endif -%}\n {%- if message['role'] == 'system' -%}\n {{ '<|im_system|>system<|im_middle|>' }}\n {%- elif message['role'] == 'user' -%}\n {{ '<|im_user|>user<|im_middle|>' }}\n {%- elif message['role'] == 'assistant' -%}\n {{ '<|im_assistant|>assistant<|im_middle|>' }}\n {%- elif message['role'] == 'tool' -%}\n {{ '<|im_system|>tool<|im_middle|>' }}\n {%- endif -%}\n\n {%- if message['content'] is string -%}\n {{- message['content'] + '<|im_end|>' -}}\n {%- else -%}\n {%- for content in message['content'] -%}\n {%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}\n {{ '<|media_start|>image<|media_content|><|media_pad|><|media_end|>' }}\n {%- else -%}\n {{ content['text'] }}\n {%- endif -%}\n {%- endfor -%}\n {{ '<|im_end|>' }}\n {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n {{ '<|im_assistant|>assistant<|im_middle|>' }}\n{%- endif -%}",
|
155 |
"model_max_length": 1000000000000000019884624838656,
|
156 |
"pad_token": "[PAD]",
|
157 |
"tokenizer_class": "TikTokenTokenizer",
|