GIST-AI
/

khs-llm

@@ -3,180 +3,67 @@ license: apache-2.0
 pipeline_tag: text-generation
 library_name: transformers
 tags:
-- vllm
 ---
-<p align="center">
-  <img alt="gpt-oss-120b" src="https://raw.githubusercontent.com/openai/gpt-oss/main/docs/gpt-oss-120b.svg">
-</p>
-<p align="center">
-  <a href="https://gpt-oss.com"><strong>Try gpt-oss</strong></a> ·
-  <a href="https://cookbook.openai.com/topic/gpt-oss"><strong>Guides</strong></a> ·
-  <a href="https://arxiv.org/abs/2508.10925"><strong>Model card</strong></a> ·
-  <a href="https://openai.com/index/introducing-gpt-oss/"><strong>OpenAI blog</strong></a>
-</p>
-<br>
-Welcome to the gpt-oss series, [OpenAI’s open-weight models](https://openai.com/open-models) designed for powerful reasoning, agentic tasks, and versatile developer use cases.
-We’re releasing two flavors of these open models:
-- `gpt-oss-120b` — for production, general purpose, high reasoning use cases that fit into a single 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters)
-- `gpt-oss-20b` — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
-Both models were trained on our [harmony response format](https://github.com/openai/harmony) and should only be used with the harmony format as it will not work correctly otherwise.
-> [!NOTE]
-> This model card is dedicated to the larger `gpt-oss-120b` model. Check out [`gpt-oss-20b`](https://huggingface.co/openai/gpt-oss-20b) for the smaller model.
-# Highlights
-* **Permissive Apache 2.0 license:** Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
-* **Configurable reasoning effort:** Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
-* **Full chain-of-thought:** Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
-* **Fine-tunable:** Fully customize models to your specific use case through parameter fine-tuning.
-* **Agentic capabilities:** Use the models’ native capabilities for function calling, [web browsing](https://github.com/openai/gpt-oss/tree/main?tab=readme-ov-file#browser), [Python code execution](https://github.com/openai/gpt-oss/tree/main?tab=readme-ov-file#python), and Structured Outputs.
-* **MXFP4 quantization:** The models were post-trained with MXFP4 quantization of the MoE weights, making `gpt-oss-120b` run on a single 80GB GPU (like NVIDIA H100 or AMD MI300X) and the `gpt-oss-20b` model run within 16GB of memory. All evals were performed with the same MXFP4 quantization.
----
-# Inference examples
-## Transformers
-You can use `gpt-oss-120b` and `gpt-oss-20b` with Transformers. If you use the Transformers chat template, it will automatically apply the [harmony response format](https://github.com/openai/harmony). If you use `model.generate` directly, you need to apply the harmony format manually using the chat template or use our [openai-harmony](https://github.com/openai/harmony) package.
-To get started, install the necessary dependencies to setup your environment:
-```
-pip install -U transformers kernels torch
-```
-Once, setup you can proceed to run the model by running the snippet below:
-```py
-from transformers import pipeline
-import torch
-model_id = "openai/gpt-oss-120b"
-pipe = pipeline(
-    "text-generation",
-    model=model_id,
-    torch_dtype="auto",
-    device_map="auto",
-)
-messages = [
-    {"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
-]
-outputs = pipe(
-    messages,
-    max_new_tokens=256,
-)
-print(outputs[0]["generated_text"][-1])
-```
-Alternatively, you can run the model via [`Transformers Serve`](https://huggingface.co/docs/transformers/main/serving) to spin up a OpenAI-compatible webserver:
-```
-transformers serve
-transformers chat localhost:8000 --model-name-or-path openai/gpt-oss-120b
-```
-[Learn more about how to use gpt-oss with Transformers.](https://cookbook.openai.com/articles/gpt-oss/run-transformers)
-## vLLM
-vLLM recommends using [uv](https://docs.astral.sh/uv/) for Python dependency management. You can use vLLM to spin up an OpenAI-compatible webserver. The following command will automatically download the model and start the server.
-```bash
-uv pip install --pre vllm==0.10.1+gptoss \
-    --extra-index-url https://wheels.vllm.ai/gpt-oss/ \
-    --extra-index-url https://download.pytorch.org/whl/nightly/cu128 \
-    --index-strategy unsafe-best-match
-vllm serve openai/gpt-oss-120b
-```
-[Learn more about how to use gpt-oss with vLLM.](https://cookbook.openai.com/articles/gpt-oss/run-vllm)
-## PyTorch / Triton
-To learn about how to use this model with PyTorch and Triton, check out our [reference implementations in the gpt-oss repository](https://github.com/openai/gpt-oss?tab=readme-ov-file#reference-pytorch-implementation).
-## Ollama
-If you are trying to run gpt-oss on consumer hardware, you can use Ollama by running the following commands after [installing Ollama](https://ollama.com/download).
-```bash
-# gpt-oss-120b
-ollama pull gpt-oss:120b
-ollama run gpt-oss:120b
-```
-[Learn more about how to use gpt-oss with Ollama.](https://cookbook.openai.com/articles/gpt-oss/run-locally-ollama)
-#### LM Studio
-If you are using [LM Studio](https://lmstudio.ai/) you can use the following commands to download.
-```bash
-# gpt-oss-120b
-lms get openai/gpt-oss-120b
-```
-Check out our [awesome list](https://github.com/openai/gpt-oss/blob/main/awesome-gpt-oss.md) for a broader collection of gpt-oss resources and inference partners.
----
-# Download the model
-You can download the model weights from the [Hugging Face Hub](https://huggingface.co/collections/openai/gpt-oss-68911959590a1634ba11c7a4) directly from Hugging Face CLI:
-```shell
-# gpt-oss-120b
-huggingface-cli download openai/gpt-oss-120b --include "original/*" --local-dir gpt-oss-120b/
-pip install gpt-oss
-python -m gpt_oss.chat model/
-```
-# Reasoning levels
-You can adjust the reasoning level that suits your task across three levels:
-* **Low:** Fast responses for general dialogue.
-* **Medium:** Balanced speed and detail.
-* **High:** Deep and detailed analysis.
-The reasoning level can be set in the system prompts, e.g., "Reasoning: high".
-# Tool use
-The gpt-oss models are excellent for:
-* Web browsing (using built-in browsing tools)
-* Function calling with defined schemas
-* Agentic operations like browser tasks
-# Fine-tuning
-Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
-This larger model `gpt-oss-120b` can be fine-tuned on a single H100 node, whereas the smaller [`gpt-oss-20b`](https://huggingface.co/openai/gpt-oss-20b) can even be fine-tuned on consumer hardware.
-# Citation
-```bibtex
-@misc{openai2025gptoss120bgptoss20bmodel,
-      title={gpt-oss-120b & gpt-oss-20b Model Card},
-      author={OpenAI},
-      year={2025},
-      eprint={2508.10925},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2508.10925},
-}
-```

 pipeline_tag: text-generation
 library_name: transformers
 tags:
+- cultural-heritage
+- government
+- fine-tuning
 ---
+# 국가유산청 특화 파인튜닝 모델 카드
+본 문서는 **국가유산청)** 업무를 지원하기 위해 파인튜닝된 대규모 언어 모델이다.
+본 모델은 공공 행정, 문화유산 관리, 학술 연구, 정책 지원을 목적으로 설계되었으며, 내부 업무 효율성과 전문성 강화를 목표로 한다.
+## 모델 개요
+- **기반 모델:** gpt-oss-120b (OpenAI open-weight model)
+- **모델 유형:** 텍스트 생성 / 추론 특화 대규모 언어 모델
+- **파라미터 규모:** 117B (MoE 구조, 활성 파라미터 약 5.1B)
+- **라이선스:** Apache 2.0 (공공기관 활용 및 내부 커스터마이징 허용)
+## 파인튜닝 목적
+본 모델은 다음과 같은 국가유산청 고유 업무를 지원하도록 파인튜닝되었다.
+- 국가유산(유·무형, 자연유산 포함) 관련 문서 요약 및 분석
+- 문화유산 정책·법령·행정 문서 초안 작성 지원
+- 조사·발굴·보존·복원 관련 기술 문서 이해 및 질의응답
+- 학술 보고서, 연구 자료, 내부 보고용 텍스트 생성
+- 대국민 설명 자료 및 교육용 콘텐츠 초안 생성(내부 검토용)
+※ 본 모델은 **최종 대외 공개 콘텐츠 자동 생성**을 목적으로 하지 않으며, 반드시 담당자의 검토를 전제로 사용한다.
+## 데이터 및 학습 범위
+- 공개 가능한 문화유산 관련 법령, 제도, 정책 문서
+- 학술 논문, 보고서, 백서 등 공공 목적 자료
+- 한국어 중심, 필요 시 다국어 참고 문헌 포함
+개인정보, 비공개 정보, 민감 데이터는 학습 데이터에서 제외되었다.
+## 추론 및 사용 특성
+- **Reasoning Level:** 중~고 (정책·학술 분석에 적합)
+- **응답 성향:** 사실 기반, 설명 중심, 행정·학술 문체
+- **체인 오브 소트:** 내부 디버깅 및 검증 목적 사용 (대외 비공개)
+## 권장 사용 환경
+- 단일 80GB GPU (NVIDIA H100 또는 동급)
+- Transformers 또는 vLLM 기반 추론 환경
+- 내부 전산망 또는 보안이 확보된 서버 환경
+## 제한 사항 및 주의점
+- 법적 해석, 정책 결정, 행정 판단의 최종 근거로 사용 불가
+- 역사·고고학적 해석은 학계의 다양한 견해 중 하나로 제시될 수 있음
+- 최신 법령 개정 사항은 별도 검증 필요
+## 활용 예시
+- “경복궁 근정전에 대한 학술적 보존 연구 정리”
+- “조선시대 목조건축 보존 기법 관련 연구 정리”
+## 책임 및 윤리
+본 모델은 **국가유산의 공공성, 학술적 엄정성, 행정적 중립성**을 최우선 가치로 설계되었다.
+모델 출력물에 대한 최종 책임은 이를 활용하는 기관 및 담당자에게 있다.