Ovis2.6-80B-A3B / tokenizer_config.json
songrui
Upload Ovis2.6-80B-A3B model files
0c3b3bb
{
"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|>",
"<image>",
"<video>",
"<ovis_visual_atom>",
"<ovis_image_start>",
"<ovis_image_end>",
"<ovis_video_start>",
"<ovis_video_end>"
],
"bos_token": null,
"chat_template": "{%- for message in messages %}\n{{- '<|im_start|>' + message.role + '\\n' }}\n{%- if message.role == 'system' or message.role == 'user' %}\n{%- if message.content is string %}\n{{- message.content }}\n{%- else %}\n{%- for item in message.content %}\n{%- if item.type == 'text' and 'text' in item %}\n{{- item.text }}\n{%- elif item.type == 'image' %}\n{{- '<image>' }}\n{%- elif item.type == 'video' %}\n{{- '<video>' }}\n{%- else %}\n{{- raise_exception('Invalid content type. Supported types for system and user are text, image, video.') }}\n{%- endif %}\n{%- if not loop.last %}{{- '\\n' }}{%- endif %}\n{%- endfor %}\n{%- endif %}\n{%- elif message.role == 'assistant' %}\n{%- set content = '' %}\n{%- if message.content is string %}\n{%- set content = message.content %}\n{%- else %}\n{%- set ns = namespace(content='') -%}\n{%- for item in message.content %}\n{%- if item.type == 'text' and 'text' in item %}\n{%- set ns.content = ns.content ~ item.text %}\n{%- else %}\n{{- raise_exception('Invalid content type. Supported type for assistant is text.') }}\n{%- endif %}\n{%- endfor %}\n{%- set content = ns.content -%}\n{%- endif %}\n{%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n{{- content }}\n{%- else %}\n{{- raise_exception('Invalid role. Supported roles are system, user, assistant.') }}\n{%- endif %}\n{{- '<|im_end|>\\n' }}\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 %}\n",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}