{
 "id": "LLM-OS-Models/KoHRM-Text-1.4B-prepared-data",
 "owner": "LLM-OS-Models",
 "name": "KoHRM-Text-1.4B-prepared-data",
 "downloads": 715,
 "likes": 1,
 "last_modified": "2026-05-24T22:52:11.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "Major sources used while constructing these prepared datasets:\n\n| Source | Link / origin | Usage |\n|---|---|---|\n| HRM-Text cleaned data | https://huggingface.co/datasets/sapientinc/HRM-Text-data-io-cleaned-20260515 | Retokenized sample and fast-cap stage-1 data |\n| HRM-Text code/paper | https://github.com/sapientinc/HRM-Text, https://arxiv.org/html/2605.20613 | Training format, PrefixLM objective, V1Dataset style |\n| Korean Wikipedia | https://dumps.wikimedia.org/kowiki/20260501/ | Korean general/wiki text |\n| Korean statutes | https://github.com/legalize-kr/legalize-kr | Korean legal raw text and task data |\n| Korean local ordinances | https://github.com/legalize-kr/ordinance-kr | Korean local law raw text |\n| Korean administrative rules | local Markdown snapshot at `/home/work/.projects/LLM-OS-Models/Terminal/admrule-kr` | Korean administrative-rule text and task rows |\n| Korean precedents | local Markdown snapshot at `/home/work/.projects/LLM-OS-Models/Terminal/precedent-kr` | Korean precedent text and task rows |\n| ToolBench | local `data_toolbench` extraction from ToolBench train data | Tool-call/API/JSON trajectories; eval split excluded |\n| SWE-ZERO | https://huggingface.co/datasets/AlienKevin/SWE-ZERO-12M-trajectories | Terminal/code trajectory subset |\n| GLM reasoning | https://huggingface.co/datasets/Jackrong/GLM-5.1-Reasoning-1M-Cleaned | Reasoning/instruction subset |\n| Claude reasoning sample | https://huggingface.co/datasets/angrygiraffe/claude-opus-4.6-4.7-rea",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "d5b8f9435227ca6b340b4c40fe7b248f9419371d",
 "stated_evidence": "https://huggingface.co/datasets/LLM-OS-Models/KoHRM-Text-1.4B-prepared-data/blob/d5b8f9435227ca6b340b4c40fe7b248f9419371d/README.md",
 "file_evidence": "https://huggingface.co/datasets/LLM-OS-Models/KoHRM-Text-1.4B-prepared-data/tree/d5b8f9435227ca6b340b4c40fe7b248f9419371d",
 "card_nc": false
}