{ "vocab_size": 131072, "requested_vocab_size": 131072, "max_gib": 2.5, "max_mib_per_input": 256.0, "min_frequency": 2, "special_tokens": [ "<|PAD|>", "<|unk|>", "<|im_start|>", "<|im_end|>", "<|system|>", "<|user|>", "<|assistant|>", "<|tool_call|>", "<|/tool_call|>", "<|tool_response|>", "<|function|>", "<|/function|>", "<|execute|>", "<|result|>", "<|terminal|>", "<|/terminal|>", "<|command|>", "<|output|>", "<|error|>", "<|exit_code|>", "<|json_start|>", "<|json_end|>", "<|xml_start|>", "<|xml_end|>", "<|code_start|>", "<|code_end|>", "", "", "<|direct|>", "<|cot|>", "<|noisy|>", "<|synth|>", "<|object_ref_start|>", "<|object_ref_end|>", "<|box_start|>", "<|box_end|>", "<|quad_start|>", "<|quad_end|>", "<|vision_start|>", "<|vision_end|>", "<|vision_pad|>", "<|image_pad|>", "<|video_pad|>", "<|fim_prefix|>", "<|fim_middle|>", "<|fim_suffix|>" ], "inputs": [ "HRM-Text/legalize-kr", "HRM-Text/ordinance-kr", "admrule-kr", "precedent-kr", "dataset", "HRM-Text/data_toolbench/data", "/home/work/.data/huggingface/hrm_text_extra/sft", "/home/work/.data/huggingface/hrm_text_extra/tokenizer_corpus", "/home/work/.data/huggingface/hrm_text_extra/raw/angrygiraffe__claude-opus-4.6-4.7-reasoning-8.7k" ] }