max_seq_len: 4096
tokenizer_info:
  boq: <|im_start|>
  condition_mapping:
    cot: <|object_ref_end|>
    direct: <|object_ref_start|>
    noisy: <|quad_start|>
    synth: <|quad_end|>
  eoa: <|box_end|>
  eoq: <|im_end|>
  tokenizer_path: /home/work/.data/hrm_text_prepared/koterm_pretrain_mix_v1
total_length: 711277327
vocab_size: 131072