IQuest-Coder-V1-14B-Thinking / tokenizer_config.json
zwpride-iquestlab's picture
Update tokenizer_config.json
1fa15f7 verified
{
"add_bos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true,
"special": true
},
"75858": {
"content": "<CLS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75859": {
"content": "<SEP>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75860": {
"content": "<EOD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75861": {
"content": "<MASK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75862": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75863": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75864": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75865": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75866": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75867": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75868": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75869": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75870": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75871": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75872": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"75873": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"75874": {
"content": "<tools>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"75875": {
"content": "</tools>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"75876": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"75877": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"75878": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"75879": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|CLS|>",
"<|SEP|>",
"<|EOD|>",
"<|MASK|>",
"<|PAD|>",
"<|fim_prefix|>",
"<|fim_middle|>",
"<|fim_suffix|>",
"<|im_start|>",
"<|im_end|>",
"<|fim_pad|>",
"<|endoftext|>",
"<|repo_name|>",
"<|file_sep|>"
],
"auto_map": {
"AutoTokenizer": [
"tokenization_iquestcoder.IQuestCoderTokenizer",
null
]
},
"bos_token": "<s>",
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- else %}\n {{- 'You are IQuest-Coder, a helpful assistant developed by IQuest.' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {%- if tool.type == 'function' and tool.function %}\n {%- set func = tool.function %}\n {%- else %}\n {%- set func = tool %}\n {%- endif %}\n {{- \"\\n<function>\\n<name>\" + func.name + \"</name>\" }}\n {%- if func.description %}\n {{- \"\\n<description>\" + func.description + \"</description>\" }}\n {%- endif %}\n {{- \"\\n<parameters>\" }}\n {%- if func.parameters and func.parameters.properties %}\n {%- for param_name, param_fields in func.parameters.properties.items() %}\n {{- \"\\n<parameter>\" }}\n {{- \"\\n<name>\" + param_name + \"</name>\" }}\n {%- if param_fields.type %}\n {{- \"\\n<type>\" + param_fields.type + \"</type>\" }}\n {%- endif %}\n {%- if param_fields.description %}\n {{- \"\\n<description>\" + param_fields.description + \"</description>\" }}\n {%- endif %}\n {{- \"\\n</parameter>\" }}\n {%- endfor %}\n {%- endif %}\n {{- \"\\n</parameters>\\n</function>\" }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nIf you choose to call a function ONLY reply in the following format:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n</function>\\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 {%- else %}\n {{- '<|im_start|>system\\nYou are IQuest-Coder, a helpful assistant developed by IQuest.<|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\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\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 {%- set has_think = false %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- set has_think = true %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set has_think = true %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and has_think) %}\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 {%- if has_think %}\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 {%- 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 tc = tool_call.function %}\n {%- else %}\n {%- set tc = tool_call %}\n {%- endif %}\n {{- '<tool_call>\\n<function=' + tc.name + '>\\n' }}\n {%- if tc.arguments is string %}\n {%- set args = tc.arguments | fromjson %}\n {%- else %}\n {%- set args = tc.arguments %}\n {%- endif %}\n {%- for arg_name, arg_value in args.items() %}\n {{- '<parameter=' + arg_name + '>\\n' }}\n {%- if arg_value is string %}\n {{- arg_value }}\n {%- else %}\n {{- arg_value | tojson }}\n {%- endif %}\n {{- '\\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.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\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 {%- endif %}\n{%- endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"sp_model_kwargs": {},
"split_special_tokens": false,
"tokenizer_class": "IQuestCoderTokenizer",
"unk_token": "<unk>",
"use_fast": false
}