Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +2 -2
tokenizer_config.json
CHANGED
|
@@ -33,5 +33,5 @@
|
|
| 33 |
"video_token": "<|video_pad|>",
|
| 34 |
"vision_bos_token": "<|vision_start|>",
|
| 35 |
"vision_eos_token": "<|vision_end|>",
|
| 36 |
-
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\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.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 is defined and add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.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 is defined and add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif '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{%- set ns_flags = namespace(enable_thinking=true) %}\n{%- if enable_thinking is defined %}\n {%- set ns_flags.enable_thinking = enable_thinking %}\n{%- endif %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\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 {%- if messages[0].role == 'system' or messages[0].role == 'developer' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if '<|think_off|>' in content %}\n {%- set ns_flags.enable_thinking = false %}\n {%- set content = content.replace('<|think_off|>', '') %}\n {%- endif %}\n {%- if '<|think_on|>' in content %}\n {%- set ns_flags.enable_thinking = true %}\n {%- set content = content.replace('<|think_on|>', '') %}\n {%- endif %}\n {%- set content = content.strip() %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' or messages[0].role == 'developer' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if '<|think_off|>' in content %}\n {%- set ns_flags.enable_thinking = false %}\n {%- set content = content.replace('<|think_off|>', '') %}\n {%- endif %}\n {%- if '<|think_on|>' in content %}\n {%- set ns_flags.enable_thinking = true %}\n {%- set content = content.replace('<|think_on|>', '') %}\n {%- endif %}\n {%- set content = content.strip() %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\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\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {%- set ns.last_query_index = messages|length - 1 %}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if '<|think_off|>' in content %}\n {%- set ns_flags.enable_thinking = false %}\n {%- set content = content.replace('<|think_off|>', '') %}\n {%- endif %}\n {%- if '<|think_on|>' in content %}\n {%- set ns_flags.enable_thinking = true %}\n {%- set content = content.replace('<|think_on|>', '') %}\n {%- endif %}\n {%- set content = content.strip() %}\n {%- if message.role == \"system\" or message.role == \"developer\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\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 string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- set has_think_tag = false %}\n {%- set think_end_token = '</think>' %}\n {%- if '</think>' in content %}\n {%- set has_think_tag = true %}\n {%- elif '</thinking>' in content %}\n {%- set has_think_tag = true %}\n {%- set think_end_token = '</thinking>' %}\n {%- elif '<think>' in content %}\n {%- set reasoning_content = content.split('<think>')[-1].lstrip('\\n') %}\n {%- set content = '' %}\n {%- endif %}\n {%- if has_think_tag %}\n {%- set reasoning_content = content.split(think_end_token)[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split(think_end_token)[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- set show_think = false %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- set show_think = true %}\n {%- elif ns_flags.enable_thinking and (preserve_thinking is undefined or preserve_thinking is true) and reasoning_content|length > 0 %}\n {%- set show_think = true %}\n {%- endif %}\n {%- if show_think %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined and tool_call.arguments is mapping %}\n {%- if tool_call.arguments|length > 0 %}\n {%- for args_name in tool_call.arguments %}\n {%- set args_value = tool_call.arguments[args_name] %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {%- elif tool_call.arguments is defined and tool_call.arguments is string %}\n {%- if tool_call.arguments|trim|length > 0 %}\n {{- tool_call.arguments }}\n {{- '\\n' }}\n {%- endif %}\n {%- endif %}\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\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if ns_flags.enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}"
|
| 37 |
-
}
|
|
|
|
| 33 |
"video_token": "<|video_pad|>",
|
| 34 |
"vision_bos_token": "<|vision_start|>",
|
| 35 |
"vision_eos_token": "<|vision_end|>",
|
| 36 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\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.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 is defined and add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.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 is defined and add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif '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{%- set ns_flags = namespace(enable_thinking=true) %}\n{%- if enable_thinking is defined %}\n {%- set ns_flags.enable_thinking = enable_thinking %}\n{%- endif %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\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 {%- if messages[0].role == 'system' or messages[0].role == 'developer' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if '<|think_off|>' in content %}\n {%- set ns_flags.enable_thinking = false %}\n {%- set content = content.replace('<|think_off|>', '') %}\n {%- endif %}\n {%- if '<|think_on|>' in content %}\n {%- set ns_flags.enable_thinking = true %}\n {%- set content = content.replace('<|think_on|>', '') %}\n {%- endif %}\n {%- set content = content.strip() %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' or messages[0].role == 'developer' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if '<|think_off|>' in content %}\n {%- set ns_flags.enable_thinking = false %}\n {%- set content = content.replace('<|think_off|>', '') %}\n {%- endif %}\n {%- if '<|think_on|>' in content %}\n {%- set ns_flags.enable_thinking = true %}\n {%- set content = content.replace('<|think_on|>', '') %}\n {%- endif %}\n {%- set content = content.strip() %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\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\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {%- set ns.last_query_index = messages|length - 1 %}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if '<|think_off|>' in content %}\n {%- set ns_flags.enable_thinking = false %}\n {%- set content = content.replace('<|think_off|>', '') %}\n {%- endif %}\n {%- if '<|think_on|>' in content %}\n {%- set ns_flags.enable_thinking = true %}\n {%- set content = content.replace('<|think_on|>', '') %}\n {%- endif %}\n {%- set content = content.strip() %}\n {%- if message.role == \"system\" or message.role == \"developer\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\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 {#- Auto-close unclosed think before tool_call -#}\n {%- if '<think>' in content and '<tool_call>' in content %}\n {%- set last_think = content.rfind('<think>') %}\n {%- set last_close = content.rfind('</think>') %}\n {%- set tool_pos = content.find('<tool_call>') %}\n {%- if last_close < last_think or last_close == -1 %}\n {%- if tool_pos > last_think %}\n {%- set content = content[:tool_pos] + '</think>' + content[tool_pos:] %}\n {%- else %}\n {%- set content = content + '</think>' %}\n {%- endif %}\n {%- endif %}\n {%- endif %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- set has_think_tag = false %}\n {%- set think_end_token = '</think>' %}\n {%- if '</think>' in content %}\n {%- set has_think_tag = true %}\n {%- elif '</thinking>' in content %}\n {%- set has_think_tag = true %}\n {%- set think_end_token = '</thinking>' %}\n {%- elif '<think>' in content %}\n {%- set reasoning_content = content.split('<think>')[-1].lstrip('\\n') %}\n {%- set content = '' %}\n {%- endif %}\n {%- if has_think_tag %}\n {%- set reasoning_content = content.split(think_end_token)[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split(think_end_token)[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- set show_think = false %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- set show_think = true %}\n {%- elif ns_flags.enable_thinking and (preserve_thinking is undefined or preserve_thinking is true) and reasoning_content|length > 0 %}\n {%- set show_think = true %}\n {%- endif %}\n {%- if show_think %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined and tool_call.arguments is mapping %}\n {%- if tool_call.arguments|length > 0 %}\n {%- for args_name in tool_call.arguments %}\n {%- set args_value = tool_call.arguments[args_name] %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {%- elif tool_call.arguments is defined and tool_call.arguments is string %}\n {%- if tool_call.arguments|trim|length > 0 %}\n {{- tool_call.arguments }}\n {{- '\\n' }}\n {%- endif %}\n {%- endif %}\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\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if ns_flags.enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}\n"
|
| 37 |
+
}
|