JiRack-UltraPro-Tokenizer-512K / tokenizer_config.json
kgrabko's picture
Upload folder using huggingface_hub
a6c6257 verified
Raw
History Blame Contribute Delete
2.77 kB
{
"tokenizer_class": "PreTrainedTokenizerFast",
"model_max_length": 8192,
"vocab_size": 524288,
"clean_up_tokenization_spaces": false,
"add_bos_token": false,
"add_eos_token": false,
"padding_side": "right",
"unk_token": "<|unk|>",
"pad_token": "<|padding|>",
"eos_token": "<|endoftext|>",
"bos_token": "<|endoftext|>",
"chat_template": "{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"additional_special_tokens": [
"<|unk|>", "<|endoftext|>", "<|padding|>", "<|im_start|>", "<|im_end|>",
"<|im_start|>system", "<|im_start|>user", "<|im_start|>assistant",
"<|im_start|>tool", "<|im_start|>function", "<|im_start|>thought",
"<|tool_call|>", "<|tool_response|>",
"<|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|>",
"__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__"
]
}