tokenizer_config.json

{
  "add_prefix_space": false,
  "audio_bos_token": "<|audio_start|>",
  "audio_eos_token": "<|audio_end|>",
  "audio_token": "<|audio_pad|>",
  "backend": "tokenizers",
  "bos_token": null,
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "errors": "replace",
  "image_token": "<|image_pad|>",
  "is_local": false,
  "max_length": null,
  "model_max_length": 262144,
  "model_specific_special_tokens": {
    "audio_bos_token": "<|audio_start|>",
    "audio_eos_token": "<|audio_end|>",
    "audio_token": "<|audio_pad|>",
    "image_token": "<|image_pad|>",
    "video_token": "<|video_pad|>",
    "vision_bos_token": "<|vision_start|>",
    "vision_eos_token": "<|vision_end|>"
  },
  "pad_to_multiple_of": null,
  "pad_token": "<|endoftext|>",
  "pad_token_type_id": 0,
  "padding_side": "left",
  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
  "processor_class": "Qwen3VLProcessor",
  "split_special_tokens": false,
  "tokenizer_class": "Qwen2Tokenizer",
  "unk_token": null,
  "video_token": "<|video_pad|>",
  "vision_bos_token": "<|vision_start|>",
  "vision_eos_token": "<|vision_end|>",
  "chat_template": "{# Define the macros for XML conversion #}\n{%- macro render_item_list(item_list, tag_name='required') -%}\n  {%- if item_list is defined and item_list is iterable and item_list | length > 0 -%}\n    <{{ tag_name }}>[{{- item_list | join(\", \") -}}]</{{ tag_name }}>\n  {%- endif -%}\n{%- endmacro -%}\n\n{%- macro render_extra_keys(json_dict, handled_keys) -%}\n  {%- if json_dict is mapping -%}\n    {%- for json_key in json_dict if json_key not in handled_keys -%}\n      <{{ json_key }}>{{ json_dict[json_key] }}</{{ json_key }}>\n    {%- endfor -%}\n  {%- endif -%}\n{%- endmacro -%}\n\n\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- set add_vision_id = add_vision_id if add_vision_id is defined else true %}\n\n{# Set Instruct mode here #}\n\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or (item is mapping and item.get('type') == 'image') %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or (item is mapping and item.get('type') == 'video') %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif item is mapping and 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n\n{# Flag to prevent double-rendering system prompt #}\n{%- set ns = namespace(system_rendered=false) %}\n\n{%- if tools and tools is iterable and tools is not mapping %}\n\n    {{- '<|im_start|>system\\n# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>' -}}\n    {%- for tool in tools -%}\n        {%- set function = tool.function -%}\n        {{- \"\\n<tool>\\n<name>\" + function.name + \"</name>\\n<description>\" + function.description + \"</description>\" -}}\n        {%- if function.parameters and function.parameters.properties -%}\n            {%- for param_name, param_details in function.parameters.properties.items() -%}\n                {{- \"\\n<parameter>\\n<name>\" + param_name + \"</name>\\n<type>\" + param_details.type + \"</type>\\n<description>\" + (param_details.description | default('')) + \"</description>\" -}}\n                {{- render_item_list(function.parameters.required) -}}\n                {{- render_extra_keys(param_details, ['type', 'description']) -}}\n                {{- \"\\n</parameter>\" -}}\n            {%- endfor -%}\n        {%- endif -%}\n        {{- \"\\n</tool>\" -}}\n    {%- endfor -%}\n\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    \n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n        {%- set ns.system_rendered = true %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n        {%- set ns.system_rendered = true %}\n    {%- endif %}\n{%- endif %}\n\n{# Main Message Loop #}\n{%- for message in messages %}\n    {%- if message.role == \"system\" and ns.system_rendered and loop.first %}\n        {%- continue %}\n    {%- endif %}\n\n    {%- set content = render_content(message.content, true)|trim %}\n    \n    {%- if message.role == \"system\" %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content | trim %}\n        {%- elif '<think>' in content and '</think>' in content %}\n            {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] | trim %}\n            {%- set content = content.split('</think>')[-1] | trim %}\n        {%- endif %}\n\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        \n        {%- if reasoning_content %}\n            {{- '<think>\\n' + reasoning_content + '\\n</think>\\n\\n' }}\n        {%- endif %}\n        \n        {{- content }}\n\n        {# Tool call formatting #}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- set tc = tool_call.function if tool_call.function is defined else tool_call %}\n                {%- if loop.first and content %}{{- '\\n\\n' }}{%- elif not loop.first %}{{- '\\n' }}{%- endif %}\n                {{- '<tool_call>\\n<function=' + tc.name + '>\\n' }}\n                {%- for args_name, args_value in tc.arguments|items %}\n                    {{- '<parameter=' + args_name + '>\\n' }}\n                    {{- (args_value | tojson | safe if args_value is mapping or args_value is sequence else args_value | string) + '\\n</parameter>\\n' }}\n                {%- endfor %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}{{- '<|im_start|>user' }}{%- endif %}\n        {{- '\\n<tool_response>\\n' + content + '\\n</tool_response>' }}\n        {%- if loop.last or (loop.nextitem and loop.nextitem.role != \"tool\") %}{{- '<|im_end|>\\n' }}{%- endif %}\n    {%- endif %}\n{%- endfor %}\n\n{# Final Generation Prompt #}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}"
}