Files
model4_dapo_16bit/tokenizer_config.json

244 lines
8.8 KiB
JSON
Raw Normal View History

{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"max_length": null,
"model_max_length": 327680,
"pad_to_multiple_of": null,
"pad_token": "<|endoftext|>",
"pad_token_type_id": 0,
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"chat_template": "{% macro render_content(content) %}{% if content is none %}{{- \"\" }}{% elif content is string %}{{- content }}{% elif content is mapping %}{{- content['value'] if 'value' in content else content['text'] }}{% elif content is iterable %}{% for item in content %}{% if item.type == 'text' %}{{- item['value'] if 'value' in item else item['text'] }}{% elif item.type == 'image' %}<im_patch>{% endif %}{% endfor %}{% endif %}{% endmacro %}{%- if tools %}{{- '<|im_start|>system\n' }}{%- if messages[0]['role'] == 'system' %}{{- render_content(messages[0]['content']) }}{%- else %}{{- '' }}{%- endif %}{{- \"\n\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>\" }}{%- for tool in tools %}{{- \"\n\" }}{{- tool | tojson }}{%- endfor %}{{- \"\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><|im_end|>\n\" }}{%- else %}{%- if messages[0]['role'] == 'system' %}{{- '<|im_start|>system\n' + render_content(messages[0]['content']) + '<|im_end|>\n' }}{%- endif %}{%- endif %}{%- for message in messages %}{%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}{{- '<|im_start|>' + message.role + '\n' + render_content(message.content) + '<|im_end|>' + '\n' }}{%- elif message.role == \"assistant\" %}{%- if loop.last %}{{- '<|im_start|>assistant\n<think>\n' + render_content(message.reasoning_content) + '\n</think>\n' + render_content(message.content) }}{%- if message.tool_calls %}{%- for tool_call in message.tool_calls %}{%- set call_details = tool_call.function if tool_call.function is defined else tool_call %}{%- set tool_call_id = tool_call.id if tool_call.id is defined else tool_call.tool_call_id %}{{- '\n<tool_call>\n{\"tool_call_id\": \"' + tool_call_id + '\", \"name\": \"' + call_details.name + '\", \"arguments\": ' }}{% if call_details.arguments is string %}{{- call_details.arguments }}{% else %}{{- call_details.arguments | tojson }}{% endif %}{{- '}\n</tool_call>' }}{%- endfor %}{%- endif %}{{- '<|im_end|>\n' }}{%- else %}{{- '<|im_start|>assistant\n' + render_content(message.content) }}{%- if message.tool_calls %}{%- for tool_call in message.tool_calls %}{%- set call_details = tool_call.function if tool_call.function is defined else tool_call %}{%- set tool_call_id = tool_call.id if tool_call.id is defined else tool_call.tool_call_id %}{{- '\n<tool_call>\n{\"tool_call_id\": \"' + tool_call_id + '\", \"name\": \"' + call_details.name + '\", \"arguments\": ' }}{% if call_details.arguments is string %}{{- call_details.arguments }}{% else %}{{- call_details.arguments | tojson }}{% endif %}{{- '}\n</tool_call>' }}{%- endfor %}{%- endif %}{{- '<|im_end|>\n' }}{%- endif %}\n{%- elif message.role in [\"tool_response\", \"tool\"] %}\n {%- if loop.first or loop.previtem.role not in [\"tool\", \"tool_response\"] -%}\n {{- '<|im_start|>tool_response\n' -}}\n {%- endif -%}\n {{- '<tool_response>\n' + 'tool_call_id: ' + message.tool_call_id + '\n' + render_content(message.content) + '\n</tool_response>\n' -}}\n {%- if loop.last or loop.nextitem.role not in [\"tool\", \"tool_response\"] -%}\n {{- '<|im_end|>\n' -}}\n {%- endif -%}\n{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant\n<think>\n' }}{%- endif %}"
}