Isotr0py

/

Ovis2-tokenizer

like 0

Hello, this is my local config for vllm. if there any need to change this.

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": "<image>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151666": {
      "content": "<image_atom>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151667": {
      "content": "<img>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151668": {
      "content": "<pre>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151669": {
      "content": "<col>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151670": {
      "content": "<row>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151671": {
      "content": "</img>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151672": {
      "content": "<image_pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "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|>"
  ],
  "bos_token": null,
  "chat_template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}<image>\n{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "errors": "replace",
  "extra_special_tokens": {
    "image_atom": "<image_atom>",
    "image_col_sep": "<col>",
    "image_end": "</img>",
    "image_pad": "<image_pad>",
    "image_prefix": "<pre>",
    "image_row_sep": "<row>",
    "image_start": "<img>",
    "image_token": "<image>"
  },
  "image_atom": "<image_atom>",
  "image_col_sep": "<col>",
  "image_end": "</img>",
  "image_pad": "<image_pad>",
  "image_prefix": "<pre>",
  "image_row_sep": "<row>",
  "image_start": "<img>",
  "image_token": "<image>",
  "model_max_length": 131072,
  "pad_token": "<|endoftext|>",
  "split_special_tokens": false,
  "tokenizer_class": "Qwen2Tokenizer",
  "unk_token": null
}

tokenizer_config.json

{
  "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|>"
  ],
  "eos_token": {
    "content": "<|im_end|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "image_atom": "<image_atom>",
  "image_col_sep": "<col>",
  "image_end": "</img>",
  "image_pad": "<image_pad>",
  "image_prefix": "<pre>",
  "image_row_sep": "<row>",
  "image_start": "<img>",
  "image_token": "<image>",
  "pad_token": {
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  }
}