Update tokenizer_config.json
Browse files- tokenizer_config.json +2 -3
tokenizer_config.json
CHANGED
@@ -115,12 +115,11 @@
|
|
115 |
},
|
116 |
"bos_token": "[BOS]",
|
117 |
"clean_up_tokenization_spaces": false,
|
118 |
-
"eos_token": "
|
119 |
"extra_special_tokens": {},
|
120 |
"model_max_length": 262144,
|
121 |
"pad_token": "[PAD]",
|
122 |
"padding_side": "left",
|
123 |
"tokenizer_class": "TikTokenTokenizer",
|
124 |
-
"unk_token": "[UNK]"
|
125 |
-
"chat_template": "{%- if tools -%}\n <|im_system|>tool_declare<|im_middle|>\n # Tools\n {{ tools | tojson }}<|im_end|>\n{%- endif -%}\n{%- for message in messages -%}\n {%- if loop.first and messages[0]['role'] != 'system' -%}\n <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>\n {%- endif -%}\n \n {%- set role_name = message.get('name') or message['role'] -%}\n {%- if message['role'] == 'user' -%}\n <|im_user|>{{role_name}}<|im_middle|>\n {%- elif message['role'] == 'assistant' -%}\n <|im_assistant|>{{role_name}}<|im_middle|>\n {%- else -%}\n <|im_system|>{{role_name}}<|im_middle|>\n {% endif %}\n\n {%- if message['role'] == 'assistant' and message.get('tool_calls') -%}\n {%- if message['content'] -%}{{ message['content'] }}{%- endif -%}\n <|tool_calls_section_begin|>\n {%- for tool_call in message['tool_calls'] -%}\n {%- set formatted_id = tool_call['id'] -%}\n <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>\n {%- endfor -%}\n <|tool_calls_section_end|>\n {%- elif message['role'] == 'tool' -%}\n ## Return of {{ message.tool_call_id }}\n {{ message['content'] }}\n {%- elif message['content'] is string -%}\n {{ message['content'] }}\n {%- elif message['content'] is not none -%}\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 {%- endif -%}\n <|im_end|>\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|im_assistant|>assistant<|im_middle|>\n{%- endif -%}"
|
126 |
}
|
|
|
115 |
},
|
116 |
"bos_token": "[BOS]",
|
117 |
"clean_up_tokenization_spaces": false,
|
118 |
+
"eos_token": "<|im_end|>",
|
119 |
"extra_special_tokens": {},
|
120 |
"model_max_length": 262144,
|
121 |
"pad_token": "[PAD]",
|
122 |
"padding_side": "left",
|
123 |
"tokenizer_class": "TikTokenTokenizer",
|
124 |
+
"unk_token": "[UNK]"
|
|
|
125 |
}
|