LLaDA2.0-mini-preview / tokenizer_config.json
lccurious's picture
First model version
d61c06e
{
"add_bos_token": false,
"add_eos_token": false,
"bos_token": "<|startoftext|>",
"chat_template": "{% set thinking_option = 'off' %}\n{{- '<role>SYSTEM</role>' }}\n{%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n' }}\n{%- endif %}\n{%- if tools %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call>\\n\" }}\n{%- endif %}\n{{- 'detailed thinking ' + thinking_option + '<|role_end|>' }}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if message.role == \"user\" %}\n {{- '<role>HUMAN</role>' + message.content + '<|role_end|>' }}\n {%- elif message.role == \"system\" and not loop.first %}\n {{- '<role>SYSTEM</role>' + message.content + '<|role_end|>' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if reasoning_content %}\n {{- '<role>ASSISTANT</role>' + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<role>ASSISTANT</role>' + content }}\n {%- endif %}\n {%- else %}\n {{- '<role>ASSISTANT</role>' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|role_end|>' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<role>OBSERVATION</role>' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|role_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<role>ASSISTANT</role>' }}\n{%- endif %}",
"clean_up_tokenization_spaces": false,
"cls_token": "[CLS]",
"eos_token": "<|endoftext|>",
"mask_token": "<|mask|>",
"fast_tokenizer": true,
"gmask_token": "[gMASK]",
"merges_file": null,
"model_max_length": 8192,
"pad_token": "<|endoftext|>",
"tokenizer_class": "PreTrainedTokenizerFast",
"trust_remote_code": true,
"vocab_file": null
}