Warecube-KO-27B / tokenizer_config.json
Warecube's picture
upload tokenizer_config.json
de1512b verified
{
"add_prefix_space": false,
"audio_bos_token": "<|audio_start|>",
"audio_eos_token": "<|audio_end|>",
"audio_token": "<|audio_pad|>",
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"image_token": "<|image_pad|>",
"is_local": true,
"model_max_length": 262144,
"model_specific_special_tokens": {
"audio_bos_token": "<|audio_start|>",
"audio_eos_token": "<|audio_end|>",
"audio_token": "<|audio_pad|>",
"image_token": "<|image_pad|>",
"video_token": "<|video_pad|>",
"vision_bos_token": "<|vision_start|>",
"vision_eos_token": "<|vision_end|>"
},
"pad_token": "<|endoftext|>",
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
"split_special_tokens": false,
"tokenizer_class": "Qwen2TokenizerFast",
"unk_token": null,
"video_token": "<|video_pad|>",
"vision_bos_token": "<|vision_start|>",
"vision_eos_token": "<|vision_end|>",
"chat_template": "{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- if loop.first and message.role == 'system' %}\n {{- '<|im_start|>system\\n' + message.content | trim + '<|im_end|>\\n' }}\n {%- elif message.role == 'user' %}\n {{- '<|im_start|>user\\n' + message.content | trim + '<|im_end|>\\n' }}\n {%- elif message.role == 'assistant' %}\n {%- if not loop.last %}\n {{- '<|im_start|>assistant\\n' + message.content | trim + '<|im_end|>\\n' }}\n {%- else %}\n {%- set content = message.content | trim %}\n {%- if content.startswith('<think>') %}\n {{- '<|im_start|>assistant\\n' + content + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>assistant\\n<think>\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n"
}