MTNg2024/Aleph-Alpha / tokenizer_config.json
MTNg2024's picture
download
raw
8.51 kB
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"127901": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"127904": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"127906": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"127907": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"127908": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"127909": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"127910": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"127911": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"127912": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": null,
"chat_template": "{%- set _sv_reasoning_effort = reasoning_effort | default(none) -%}\n{%- set _sv_thinking_disabled = false -%}\n{%- if _sv_reasoning_effort is not none -%}\n {%- set _sv_thinking_disabled = _sv_reasoning_effort == 'none' -%}\n{%- elif enable_thinking is defined and enable_thinking is false -%}\n {%- set _sv_thinking_disabled = true -%}\n{%- endif -%}\n{%- set _sv_no_reasoning_sentence = \"Reasoning is disabled. Proceed straight to answering according to the user's instructions.\" -%}\n{%- set _sv_low_reasoning_sentence = \"Reasoning effort is set to low. Think briefly through only the essential steps in the user's language, then proceed directly to the answer.\" -%}\n{%- set _sv_medium_reasoning_sentence = \"Reasoning effort is set to medium. Think through the task methodically in the user's language, check key assumptions, and provide a well-supported answer.\" -%}\n{%- set _sv_high_reasoning_sentence = \"Reasoning effort is set to high. Think carefully through the task in the user's language, validate key assumptions, consider plausible alternatives, and prioritize correctness and clarity.\" -%}\n{%- set _sv_reasoning_sentence = _sv_high_reasoning_sentence -%}\n{%- if _sv_thinking_disabled -%}\n {%- set _sv_reasoning_sentence = _sv_no_reasoning_sentence -%}\n{%- elif _sv_reasoning_effort in ['minimal', 'low'] -%}\n {%- set _sv_reasoning_sentence = _sv_low_reasoning_sentence -%}\n{%- elif _sv_reasoning_effort == 'medium' -%}\n {%- set _sv_reasoning_sentence = _sv_medium_reasoning_sentence -%}\n{%- elif _sv_reasoning_effort in ['high', 'xhigh', 'max'] or _sv_reasoning_effort is none -%}\n {%- set _sv_reasoning_sentence = _sv_high_reasoning_sentence -%}\n{%- endif -%}\n{%- set _sv_has_system = messages | length > 0 and messages[0].role == 'system' -%}\n{%- if tools or _sv_reasoning_sentence is not none or _sv_has_system %}\n {{- '<|im_start|>system\\n' }}\n {%- if _sv_has_system %}\n {{- messages[0].content }}\n {%- endif %}\n {%- if _sv_reasoning_sentence is not none %}\n {%- if _sv_has_system %}{{- '\\n\\n' }}{%- endif %}\n {{- '# Reasoning effort\\n\\n' + _sv_reasoning_sentence }}\n {%- endif %}\n {%- if tools %}\n {%- if _sv_has_system or _sv_reasoning_sentence is not none %}{{- '\\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>\" }}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\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 message.content is string 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 if message.content is string else '' %}\n {%- set reasoning = none %}\n {%- if message.reasoning is defined and message.reasoning is not none %}\n {%- set reasoning = message.reasoning %}\n {%- elif message.reasoning_content is defined and message.reasoning_content is not none %}\n {#- Deprecated vLLM compatibility. Prefer the `reasoning` field. -#}\n {%- set reasoning = message.reasoning_content %}\n {%- elif content is string and '</think>' in content %}\n {%- set reasoning = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if (loop.index0 > ns.last_query_index) or (preserve_thinking is defined and preserve_thinking is true) %}\n {{- '<think>\\n' }}\n {%- if reasoning is not none and reasoning | trim %}\n {{- reasoning.strip('\\n') }}\n {%- endif %}\n {{- '\\n</think>\\n\\n' }}\n {%- endif %}\n {{- content.lstrip('\\n') }}\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</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 _sv_thinking_disabled %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 262144,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": null
}

Xet Storage Details

Size:
8.51 kB
·
Xet hash:
2bb360c0b4994a66f7ab7c4288af62cab57ab05ea85b5c51a5f2b92b763dfe25

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.