Spark-X2.5-4B / tokenizer_config.json
dongjiang1989's picture
Initial release of Spark-X2.5-4B
ea14618
Raw
History Blame Contribute Delete
4.8 kB
{
"add_bos_token": false,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|start▁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": 131072,
"pad_token": {
"__type": "AddedToken",
"content": "<|▁pad▁|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sp_model_kwargs": {},
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"tokenizer_class": "PreTrainedTokenizerFast",
"chat_template": "{%- if not messages %}{{- raise_exception('No messages provided.') }}{%- endif %}{%- set enable_thinking = enable_thinking | default(true) %}{#- Render a string or a list of text blocks. -#}{%- macro render_content(content, context_name) %}{%- if content is string %}{{- content }}{%- elif content is none or content is undefined %}{{- '' }}{%- elif content is iterable and content is not mapping %}{%- for block in content %}{%- if block.type == 'text' %}{{- block.text }}{%- else %}{{- raise_exception('Unsupported ' ~ context_name ~ ' content block type: ' ~ (block.type | string)) }}{%- endif %}{%- endfor %}{%- else %}{{- raise_exception(context_name ~ ' content must be a string or a list of text blocks') }}{%- endif %}{%- endmacro %}{#- Default system prompt -#}{%- set default_system = 'you are a helpful assistant.' %}{#- The first message-level system is placed in the initial system block. -#}{%- set ns = namespace(initial_system='') %}{%- if messages[0].role == 'system' %}{%- set ns.initial_system = render_content(messages[0].content, 'system') %}{%- endif %}{#- System block -#}{{- '<|start▁of▁sentence|><|System|>' + '\n' + default_system }}{%- if tools %}{{- '## Tools' + '\n' + 'You have access to the following functions:' + '\n' + '<tools>' }}{%- for tool in tools %}{{- '\n' + tool.function | tojson}}{%- endfor %}{{- '\n' + '</tools>' }}{%- endif %}{%- if ns.initial_system %}{{- '\n\n' + ns.initial_system }}{%- endif %}{{- '<|end▁of▁sentence|>'}}{#- Conversation turns -#}{%- for message in messages %}{%- if message.role == 'system' %}{#- The first system message was consumed by the initial block. -#}{%- if not loop.first %}{{- '<|start▁of▁sentence|><|System|>\n' + render_content(message.content, 'system') + '<|end▁of▁sentence|>' }}{%- endif %}{%- elif message.role == 'user' %}{{- '<|start▁of▁sentence|><|User|>' + render_content(message.content, 'user') + '<|end▁of▁sentence|>' }}{%- elif message.role == 'assistant' %}{%- set assistant_content = render_content(message.content, 'assistant') %}{%- if message.reasoning_content is defined and message.reasoning_content %}{%- set reasoning_content = message.reasoning_content %}{%- else %}{%- set reasoning_content = '' %}{%- endif %}{{- '<|start▁of▁sentence|><|Bot|>'}}{%- if reasoning_content %}{{- '<think>' + reasoning_content + '</think>'}}{%- else %}{{- '</think>' }}{%- endif %}{%- if assistant_content %}{{- assistant_content }}{%- endif %}{%- if message.tool_calls is defined and message.tool_calls is not none %}{%- for tool_call in message.tool_calls %}{%- if tool_call.function.arguments is not mapping %}{{- raise_exception('tool_call.function.arguments must be a dictionary; normalize JSON strings before apply_chat_template') }}{%- endif %}{%- set args = tool_call.function.arguments %}{{- '<tool_call>' + tool_call.function.name }}{%- for k, v in args.items() %}{{- '<arg_key>' ~ k ~ '</arg_key><arg_value>' ~ (v if v is string else v | tojson) ~ '</arg_value>' }}{%- endfor %}{{- '</tool_call>' }}{%- endfor %}{%- endif %}{{- '<|end▁of▁sentence|>' }}{%- elif message.role == 'tool' %}{%- if loop.previtem is undefined or loop.previtem.role != 'tool' %}{{- '<|start▁of▁sentence|><|Tool|>' }}{%- endif %}{{- '<tool_response>' ~ message.content ~ '</tool_response>' }}{%- if loop.nextitem is undefined or loop.nextitem.role != 'tool' %}{{- '<|end▁of▁sentence|>' }}{%- endif %}{%- else %}{{- raise_exception('Unsupported message role: ' ~ message.role) }}{%- endif %}{%- endfor %}{#- Generation prompt -#}{%- if add_generation_prompt %}{{- '<|start▁of▁sentence|><|Bot|>' }}{%- if enable_thinking is defined and enable_thinking %}{{- '<think>' }}{%- endif %}{%- if enable_thinking is defined and not enable_thinking %}{{- '</think>' }}{%- endif %}{%- endif %}"
}