Files
Akkadian-Finetune-Qwen3-4B-…/tokenizer_config.json

785 lines
22 KiB
JSON
Raw Permalink 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
},
"151669": {
"content": "<|PAD_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151670": {
"content": "<gap>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151671": {
"content": ".3333",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151672": {
"content": ".6666",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151673": {
"content": ".5",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151674": {
"content": ".8333",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151675": {
"content": "IŠTAR",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151676": {
"content": "KÙ.BABBAR",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151677": {
"content": "šu-ma",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151678": {
"content": "iš-tí",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151679": {
"content": "lim{ki}",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151680": {
"content": "iš-tù",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151681": {
"content": "mì-ma",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151682": {
"content": "PUZUR4",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151683": {
"content": "DUMU",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151684": {
"content": "GÍN",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151685": {
"content": "šùr",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151686": {
"content": "um-ma",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151687": {
"content": "URUDU",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151688": {
"content": "KIŠIB",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151689": {
"content": "ki-ma",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151690": {
"content": "AN.NA",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151691": {
"content": "DINGIR",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151692": {
"content": "ma-lá",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151693": {
"content": "a-ta",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151694": {
"content": "a-dí",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151695": {
"content": "DU10",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151696": {
"content": "TÚG",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151697": {
"content": "lúm",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151698": {
"content": "ITU.KAM",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151699": {
"content": "šu",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151700": {
"content": "a-na",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151701": {
"content": "ša",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151702": {
"content": "kà",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151703": {
"content": "ma-na",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151704": {
"content": "šur",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151705": {
"content": "iš",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151706": {
"content": "ḫa",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151707": {
"content": "mì",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151708": {
"content": "i-na",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151709": {
"content": "qí",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151710": {
"content": "IGI",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151711": {
"content": "ḫi",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151712": {
"content": "bi4",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151713": {
"content": "sú",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151714": {
"content": "ḫu",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151715": {
"content": "áš",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151716": {
"content": "ṭup",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151717": {
"content": "qá",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151718": {
"content": "šé",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151719": {
"content": "qé",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151720": {
"content": "ṣa",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151721": {
"content": "il5",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151722": {
"content": "tám",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151723": {
"content": "ṣí",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151724": {
"content": "pí",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151725": {
"content": "qú",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151726": {
"content": "aḫ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151727": {
"content": "pì",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151728": {
"content": "ṣé",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151729": {
"content": "ṣú",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151730": {
"content": "sà",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151731": {
"content": "GÚ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151732": {
"content": "kum",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151733": {
"content": "uš",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151734": {
"content": "ší-im",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151735": {
"content": "SIG5",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151736": {
"content": "šál",
"lstrip": false,
"normalized": true,
"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": {},
"model_max_length": 40960,
"pad_token": "<|PAD_TOKEN|>",
"padding_side": "left",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for forward_message in messages %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- set message = messages[index] %}\n {%- set tool_start = '<tool_response>' %}\n {%- set tool_start_length = tool_start|length %}\n {%- set start_of_message = message.content[:tool_start_length] %}\n {%- set tool_end = '</tool_response>' %}\n {%- set tool_end_length = tool_end|length %}\n {%- set start_pos = (message.content|length) - tool_end_length %}\n {%- if start_pos < 0 %}\n {%- set start_pos = 0 %}\n {%- endif %}\n {%- set end_of_message = message.content[start_pos:] %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(start_of_message == tool_start and end_of_message == tool_end) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = (message.content.split('</think>')|last).lstrip('\\n') %}\n {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\\n') %}\n {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</to
}