DeepSeek-R1/tokenizer_config.json
2025-02-09 20:10:26 +08:00

35 lines
3.5 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<begin▁of▁sentence>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "<end▁of▁sentence>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"legacy": true,
"model_max_length": 16384,
"pad_token": {
"__type": "AddedToken",
"content": "<end▁of▁sentence>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sp_model_kwargs": {},
"unk_token": null,
"tokenizer_class": "LlamaTokenizerFast",
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\\n\\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<User>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' in message %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<Assistant><tool▁calls▁begin><tool▁call▁begin>' + tool['type'] + '<tool▁sep>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<tool▁call▁end>'}}{%- else %}{{'<Assistant>' + message['content'] + '<tool▁calls▁begin><tool▁call▁begin>' + tool['type'] + '<tool▁sep>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<tool▁call▁end>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<tool▁call▁begin>' + tool['type'] + '<tool▁sep>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<tool▁call▁end>'}}{%- endif %}{%- endfor %}{{'<tool▁calls▁end><end▁of▁sentence>'}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' not in message %}{%- if ns.is_tool %}{{'<tool▁outputs▁end>' + message['content'] + '<end▁of▁sentence>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<Assistant>' + content + '<end▁of▁sentence>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<tool▁outputs▁begin><tool▁output▁begin>' + message['content'] + '<tool▁output▁end>'}}{%- set ns.is_output_first = false %}{%- else %}{{'<tool▁output▁begin>' + message['content'] + '<tool▁output▁end>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<tool▁outputs▁end>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<Assistant><think>\\n'}}{% endif %}"
}