MiniMax-M2-MLX-6bit / tokenizer_config.json
lmmy's picture
Add files using upload-large-folder tool
c9e9a9d verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"200000": {
"content": "]!p~[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200001": {
"content": "<fim_prefix>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200002": {
"content": "<fim_middle>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200003": {
"content": "<fim_suffix>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200004": {
"content": "<fim_pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200005": {
"content": "<reponame>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200006": {
"content": "<filename>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200007": {
"content": "<gh_stars>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200008": {
"content": "<issue_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200009": {
"content": "<issue_comment>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200010": {
"content": "<issue_closed>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200011": {
"content": "<jupyter_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200012": {
"content": "<jupyter_text>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200013": {
"content": "<jupyter_code>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200014": {
"content": "<jupyter_output>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200015": {
"content": "<empty_output>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200016": {
"content": "<commit_before>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200017": {
"content": "<commit_msg>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200018": {
"content": "<commit_after>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200019": {
"content": "]~b]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200020": {
"content": "[e~[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200021": {
"content": "]!d~[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200022": {
"content": "<function_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200023": {
"content": "<code_interpreter>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200024": {
"content": "]<]speech[>[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200025": {
"content": "]<]image[>[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200026": {
"content": "]<]video[>[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200027": {
"content": "]<]start of speech[>[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200028": {
"content": "]<]end of speech[>[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200029": {
"content": "]<]start of image[>[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200030": {
"content": "]<]end of image[>[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200031": {
"content": "]<]start of video[>[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200032": {
"content": "]<]end of video[>[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200033": {
"content": "]<]vision pad[>[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200034": {
"content": "]~!b[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200035": {
"content": "<jupyter_error>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200036": {
"content": "<add_file>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200037": {
"content": "<delete_file>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200038": {
"content": "<rename_file>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200039": {
"content": "<edit_file>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200040": {
"content": "<commit_message>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200041": {
"content": "<empty_source_file>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200042": {
"content": "<repo_struct>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200043": {
"content": "<code_context>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200044": {
"content": "<file_content>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200045": {
"content": "<source_files>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200046": {
"content": "<pr_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200047": {
"content": "<review_comment>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200048": {
"content": "<filepath>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200049": {
"content": "<file_sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"200050": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"200051": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"200052": {
"content": "<minimax:tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"200053": {
"content": "</minimax:tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<code_interpreter>",
"<commit_after>",
"<commit_before>",
"<commit_msg>",
"<empty_output>",
"<filename>",
"<fim_middle>",
"<fim_pad>",
"<fim_prefix>",
"<fim_suffix>",
"<function_call>",
"<gh_stars>",
"]<]speech[>[",
"]<]image[>[",
"]<]video[>[",
"]<]start of speech[>[",
"]<]end of speech[>[",
"]<]start of image[>[",
"]<]end of image[>[",
"]<]start of video[>[",
"]<]end of video[>[",
"]<]vision pad[>[",
"]~!b[",
"<issue_closed>",
"<issue_comment>",
"<issue_start>",
"<jupyter_code>",
"<jupyter_output>",
"<jupyter_start>",
"<jupyter_text>",
"<reponame>",
"[e~[",
"]!d~[",
"]!p~[",
"]~b]",
"<jupyter_error>",
"<add_file>",
"<delete_file>",
"<rename_file>",
"<edit_file>",
"<commit_message>",
"<empty_source_file>",
"<repo_struct>",
"<code_context>",
"<file_content>",
"<source_files>",
"<pr_start>",
"<review_comment>",
"<filepath>",
"<file_sep>"
],
"bos_token": "]~!b[",
"clean_up_tokenization_spaces": false,
"eos_token": "[e~[",
"extra_special_tokens": {},
"model_max_length": 40960000,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "]!d~[",
"chat_template": "{# ----------\u2011\u2011\u2011 special token variables \u2011\u2011\u2011---------- #}\n{%- set toolcall_begin_token = '<minimax:tool_call>' -%}\n{%- set toolcall_end_token = '</minimax:tool_call>' -%}\n{#- Tool Rendering Functions ============================================== -#}\n{%- macro render_tool_namespace(namespace_name, tool_list) -%}\n{%- for tool in tool_list -%}\n<tool>{{ tool.function | tojson(ensure_ascii=False) }}</tool>\n{% endfor -%}\n{%- endmacro -%}\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 {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{#- System Message Construction ============================================ -#}\n{%- macro build_system_message(system_message) -%}\n {%- if system_message and system_message.content -%}\n {{- visible_text(system_message.content) }}\n {%- else -%}\n {%- if model_identity is not defined -%}\n {%- set model_identity = \"You are a helpful assistant.\" -%}\n {%- endif -%}\n {{- model_identity }}\n {%- endif -%}\n \n {#- Handle current_date -#}\n {%- if system_message and system_message.current_date -%}\n {{- '\\n' ~ 'Current date: ' + system_message.current_date }}\n {%- endif -%}\n {#- Handle current_location -#}\n {%- if system_message and system_message.current_location -%}\n {{- '\\n' ~ 'Current location: ' + system_message.current_location }}\n {%- endif -%}\n{%- endmacro -%}\n{#- Main Template Logic ================================================= -#}\n{#- Extract system message (only first message if it's system) -#}\n{%- set system_message = none -%}\n{%- set conversation_messages = messages -%}\n{%- if messages and messages[0].role == \"system\" -%}\n {%- set system_message = messages[0] -%}\n {%- set conversation_messages = messages[1:] -%}\n{%- endif -%}\n{#- Get the last user message turn, for interleved thinking -#}\n{%- set ns = namespace(last_user_index=-1) %}\n{% for m in conversation_messages %}\n {%- if m.role == 'user' %}\n {% set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{#- Render system message -#}\n{{- ']~!b[' ~ ']~b]system' ~ '\\n' }}\n{{- build_system_message(system_message) }}\n{#- Render tools if available -#}\n{%- if tools -%}\n {{- '\\n\\n' ~ '# Tools' ~ '\\n' ~ 'You may call one or more tools to assist with the user query.\\nHere are the tools available in JSONSchema format:' ~ '\\n' }}\n {{- '\\n' ~ '<tools>' ~ '\\n' }}\n {{- render_tool_namespace(\"functions\", tools) }}\n {{- '</tools>' ~ '\\n\\n' }}\n{{- 'When making tool calls, use XML format to invoke tools and pass parameters:' ~ '\\n' }}\n{{- '\\n' ~ toolcall_begin_token }}\n<invoke name=\"tool-name-1\">\n<parameter name=\"param-key-1\">param-value-1</parameter>\n<parameter name=\"param-key-2\">param-value-2</parameter>\n...\n</invoke>\n{{- '\\n' ~ toolcall_end_token }}\n{%- endif -%}\n{{- '[e~[\\n' }}\n\n{#- Render messages -#}\n{%- set last_tool_call = namespace(name=none) -%}\n{%- for message in conversation_messages -%}\n {%- if message.role == 'assistant' -%}\n {#- Only render reasoning_content if no user message follows -#}\n {{- ']~b]ai' ~ '\\n' }}\n\n {%- set reasoning_content = '' %}\n {%- set content = visible_text(message.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].strip('\\n').split('<think>')[-1].strip('\\n') %}\n {%- set content = content.split('</think>')[-1].strip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if reasoning_content and loop.index0 > ns.last_user_index -%}\n {{- '<think>' ~ '\\n' ~ reasoning_content ~ '\\n' ~ '</think>' ~ '\\n\\n' }}\n {%- endif -%}\n {%- if content -%}\n {{- content }}\n {%- endif -%}\n {%- if message.tool_calls -%}\n {{- '\\n' ~ toolcall_begin_token ~ '\\n' }}\n\n {%- for tool_call in message.tool_calls -%}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<invoke name=\"' + tool_call.name + '\">' }}\n {% set _args = tool_call.arguments %}\n {%- for k, v in _args.items() %}\n {{- '<parameter name=\"' + k + '\">' }}\n {{- v | tojson(ensure_ascii=False) if v is not string else v }}\n {{- '</parameter>' }}\n {% endfor %}\n {{- '</invoke>' ~ '\\n' }}\n {%- endfor -%}\n \n {{- toolcall_end_token}}\n {%- set last_tool_call.name = message.tool_calls[-1].name -%}\n {%- else -%}\n {%- set last_tool_call.name = none -%}\n {%- endif -%}\n {{- '[e~[' ~ '\\n' }}\n \n {%- elif message.role == 'tool' -%}\n {%- if last_tool_call.name is none -%}\n {{- raise_exception(\"Message has tool role, but there was no previous assistant message with a tool call!\") }}\n {%- endif -%}\n {%- if loop.first or (conversation_messages[loop.index0 - 1].role != 'tool') -%}\n {{- ']~b]tool' }}\n {%- endif -%}\n {%- if message.content is string -%}\n {{- '\\n<response>' }}\n {{- message.content }}\n {{- '</response>' }}\n {%- else -%}\n {%- for tr in message.content -%}\n {{- '\\n<response>' }}\n {{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}\n {{- '\\n</response>' }}\n {%- endfor -%}\n {%- endif -%}\n {%- if loop.last or (conversation_messages[loop.index0 + 1].role != 'tool') -%}\n {{- '[e~[\\n' -}}\n {%- endif -%}\n \n {%- elif message.role == 'user' -%}\n {{- ']~b]user' ~ '\\n' }}\n {{- visible_text(message.content) }}\n {{- '[e~[' ~ '\\n' }}\n {%- endif -%}\n{%- endfor -%}\n\n{#- Generation prompt -#}\n{%- if add_generation_prompt -%}\n{{- ']~b]ai' ~ '\\n' ~ '<think>' ~ '\\n' }}\n{%- endif -%}\n"
}