tokenizer_config.json

{
  "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",
  "extra_special_tokens": [
    "<|image|>",
    "<|video|>",
    "<|sound|>",
    "<|voice|>",
    "<|listening|>",
    "<|vision|>",
    "<|mood_happy|>",
    "<|mood_sad|>",
    "<|mood_angry|>",
    "<|mood_neutral|>",
    "<fim_prefix>",
    "<fim_middle>",
    "<fim_suffix>",
    "<|action_start|>",
    "<|action_end|>",
    "<|trajectory_start|>",
    "<|trajectory_end|>",
    "<|joint_start|>",
    "<|joint_end|>",
    "<|sensor_start|>",
    "<|sensor_end|>",
    "<|command_start|>",
    "<|command_end|>",
    "<|state_start|>",
    "<|state_end|>",
    "<|pose|>",
    "<|velocity|>",
    "<|force|>",
    "<|torque|>",
    "<|gripper|>",
    "<|navigation|>",
    "<|obstacle|>",
    "<|task_start|>",
    "<|task_end|>",
    "<|plan_start|>",
    "<|plan_end|>",
    "<|behavior_start|>",
    "<|behavior_end|>",
    "<|skill_start|>",
    "<|skill_end|>",
    "<|motor|>",
    "<|servo|>",
    "<|imu|>",
    "<|lidar|>",
    "<|camera|>",
    "<|depth|>",
    "<|waypoint|>",
    "<|path|>",
    "<|collision|>",
    "<|grasp|>",
    "<|release|>",
    "<|homing|>",
    "<|emergency_stop|>",
    "<|calibration|>",
    "<|manipulation|>",
    "<|locomotion|>",
    "<|feedback|>",
    "<|control_loop|>",
    "<|language|>",
    "<|tool_call_start|>",
    "<|tool_call_end|>",
    "<|tool_result_start|>",
    "<|tool_result_end|>",
    "__SCIENCE__",
    "__CODING__",
    "__STOCK_EXCHANGE__",
    "__MEDICINE__",
    "__GOVERNMENT__",
    "__NEWS__",
    "__GENERAL__",
    "__MATERIAL_SCIENCE__",
    "__ELECTRONICS__",
    "__MICROELECTRONICS__",
    "__ENGINEERING__",
    "__ROBOTICS__",
    "__ENERGY__",
    "__AUTOMOTIVE__",
    "__AVIATION__",
    "__MATH__",
    "__PYTHON__",
    "__C__",
    "__CPP__",
    "__C_SHARP__",
    "__JAVA__",
    "__JAVASCRIPT__",
    "__TYPESCRIPT__",
    "__RUST__",
    "__GO__",
    "__RUBY__",
    "__PHP__",
    "__SWIFT__",
    "__KOTLIN__",
    "__BASH__",
    "__SQL__",
    "__ASSEMBLY__",
    "__PHILOSOPHY__",
    "__LITERATURE__",
    "__SOCIOLOGY__",
    "__PSYCHOLOGY__",
    "__POLITICAL_SCIENCE__",
    "__CULTURAL_STUDIES__",
    "__ETHNOGRAPHY__",
    "__HUMAN_RIGHTS__",
    "__COMPLIANCE__",
    "__MILITARY__",
    "__BANKING__",
    "__OIL_INDUSTRY__",
    "__LIGHT_INDUSTRY__",
    "__NATURE__",
    "__OCEAN__",
    "__SPORT__",
    "__CULINARY__",
    "__TRAVEL__",
    "__HOBBY__"
  ],
  "image_token": "<|image_pad|>",
  "is_local": false,
  "local_files_only": false,
  "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": "Qwen2Tokenizer",
  "unk_token": null,
  "video_token": "<|video_pad|>",
  "vision_bos_token": "<|vision_start|>",
  "vision_eos_token": "<|vision_end|>"
}