GLM-5.2-tokenizer / tokenizer_config.json
redkits's picture
Upload tokenizer_config.json with huggingface_hub
a26cc08 verified
Raw History Blame Contribute Delete
6.03 kB
{
"backend": "tokenizers",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": [
"<|endoftext|>",
"[MASK]",
"[gMASK]",
"[sMASK]",
"<sop>",
"<eop>",
"<|system|>",
"<|user|>",
"<|assistant|>",
"<|observation|>",
"<|begin_of_image|>",
"<|end_of_image|>",
"<|begin_of_video|>",
"<|end_of_video|>",
"<|begin_of_audio|>",
"<|end_of_audio|>",
"<|begin_of_transcription|>",
"<|end_of_transcription|>"
],
"is_local": true,
"model_max_length": 1048576,
"model_specific_special_tokens": {},
"pad_token": "<|endoftext|>",
"padding_side": "left",
"remove_space": false,
"tokenizer_class": "TokenizersBackend",
"chat_template": "[gMASK]<sop>\n{%- set effective_reasoning_effort = 'high' if reasoning_effort is defined and reasoning_effort == 'high' else 'max' -%}\n{%- if (enable_thinking is not defined or enable_thinking) and effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}\n{%- if tools -%}\n{%- macro tool_to_json(tool) -%}\n {%- set ns_tool = namespace(first=true) -%}\n {{ '{' -}}\n {%- for k, v in tool.items() -%}\n {%- if k != 'defer_loading' and k != 'strict' -%}\n {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}\n {%- set ns_tool.first = false -%}\n \"{{ k }}\": {{ v | tojson(ensure_ascii=False) }}\n {%- endif -%}\n {%- endfor -%}\n {{- '}' -}}\n{%- endmacro -%}\n<|system|>\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{%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n{%- endif -%}\n{% if tool.defer_loading is not defined or not tool.defer_loading %}\n{{ tool_to_json(tool) }}\n{% endif %}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content }}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text }}\n {%- elif item is string -%}\n {{- item }}\n {%- elif item is mapping and item.type in ['image', 'image_url', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}\n {%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%}\n {{- \"<reminder>You are unable to process this \" ~ media_type ~ \" because you don't have multi-modal input ability. Try different methods.</reminder>\" }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) -%}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {%- set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{%- for m in messages -%}\n{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- elif '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}\n {%- set content = content.split('</think>')[-1] %}\n{%- endif %}\n{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}\n{{ '<think>' + reasoning_content + '</think>'}}\n{%- else -%}\n{{ '<think></think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n {%- set tc = tc.function %}\n{%- endif %}\n{{- '<tool_call>' + tc.name -}}\n{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' -}}\n{%- endif %}\n{%- if m.content is string -%}\n {{- '<tool_response>' + m.content + '</tool_response>' -}}\n{%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0.type == \"tool_reference\" -%}\n {{- '<tool_response><tools>\\n' -}}\n {% for tr in m.content %}\n {%- for tool in tools -%}\n {%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n {%- endif -%}\n {%- if tool.name == tr.name -%}\n {{- tool_to_json(tool) + '\\n' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {{- '</tools></tool_response>' -}}\n{%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0 is mapping and m.content.0.output is defined -%}\n {%- for tr in m.content -%}\n {{- '<tool_response>' + tr.output + '</tool_response>' -}}\n {%- endfor -%}\n{%- else -%}\n {{- '<tool_response>' + visible_text(m.content) + '</tool_response>' -}}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|assistant|>{{- '<think></think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}\n{%- endif -%}\n"
}