dots.ocr

{
  "architectures": [
    "DotsOCRForCausalLM"
  ],
  "model_type": "dots_ocr",
  "auto_map": {
    "AutoConfig": "configuration_dots.DotsOCRConfig",
    "AutoModelForCausalLM": "modeling_dots_ocr.DotsOCRForCausalLM"
  },
  "processor_config": {
    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{%- for m in messages %}{%- if m.role == 'system' %}{{- '<|system|>' + m.content + '<|endofsystem|>\n' }}{%- elif m.role == 'user' %}{% if m.content is string %}{{- '<|user|>' + m.content + '<|endofuser|>' }}{% else %} {% for content in m.content %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|img|><|imgpad|><|endofimg|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|img|><|video_pad|><|endofimg|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}{%- endif %}{%- elif m.role == 'assistant' %}{{- '<|assistant|>' + m.content }}{%- if not loop.last %}{{- '<|endofassistant|>' }}{%- endif %}{%- endif %}{%- endfor %}{%- if messages[-1].role != 'assistant' %}{{- '<|assistant|>' }}{%- endif %}"
  },
  "tokenizer_config": {
    "bos_token": null,
    "chat_template": "{%- for m in messages %}\n    {%- if m.role == 'system' %}\n        {{- '<|system|>' + m.content + '<|endofsystem|>\\n' }}\n    {%- elif m.role == 'user' %}\n        {{- '<|user|>' + m.content + '<|endofuser|>' }}\n    {%- elif m.role == 'assistant' %}\n        {{- '<|assistant|>' + m.content }}\n        {%- if not loop.last %}\n            {{- '<|endofassistant|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if messages[-1].role != 'assistant' %}\n    {{- '<|assistant|>' }}\n{%- endif %}",
    "eos_token": "<|endoftext|>",
    "pad_token": "[PAD]",
    "unk_token": null
  }
}