Ovis2.5-2B/tokenizer_config.json

{
  "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 %}{{- '<|im_start|>' + message.role + '\n'}}{%- if message.role == 'system' or message.role == 'user' %}{%- if message.content is string %}{{- message.content | replace('<image>', '') | replace('<video>', '') }}{%- else %}{%- for item in message.content %}{%- if item.type == 'text' and 'text' in item %}{{- item.text | replace('<image>', '') | replace('<video>', '') }}{%- elif item.type == 'image' %}{{- '<image>'}}{%- elif item.type == 'video' %}{{- '<video>'}}{%- else %}{{- raise_exception('Invalid content type. Supported types for system and user are text, image, video.')}}{%- endif %}{%- if not loop.last %}{{- '\n'}}{%- endif %}{%- endfor %}{%- endif %}{%- elif message.role == 'assistant' %}{%- set content = '' %}{%- if message.content is string %}{%- set content = message.content | replace('<image>', '') | replace('<video>', '') %}{%- else %}{%- set ns = namespace(content='') -%}{%- for item in message.content %}{%- if item.type == 'text' and 'text' in item %}{%- set ns.content = ns.content ~ (item.text | replace('<image>', '') | replace('<video>', '')) %}{%- else %}{{- raise_exception('Invalid content type. Supported type for assistant is text.')}}{%- endif %}{%- endfor %}{%- set content = ns.content -%}{%- endif %}{%- set content = content.split('</think>')[-1].lstrip('\n') %}{{- content }}{%- else %}{{- raise_exception('Invalid role. Supported roles are system, user, assistant.')}}{%- endif %}{{- '<|im_end|>\n'}}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant\n' }}{%- if enable_thinking is defined and enable_thinking is false %}{{- '<think>\n\n</think>\n\n' }}{%- endif %}{%- endif %}",
  "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
}