---

license: apache-2.0 tags:

• generated_from_trainer base_model: yanolja/EEVE-Korean-10.8B-v1.0 model-index:
• name: yanolja/EEVE-Korean-Instruct-10.8B-v1.0 results: []

---

EEVE-Korean-Instruct-10.8B-v1.0

加入我们的Discord社区！

如果您对大语言模型领域充满热情，并希望交流知识与见解，我们诚挚邀请您加入我们的Discord服务器。请注意，该服务器主要使用韩语进行交流。LLM领域正在快速发展，若缺乏积极分享，我们的集体知识可能会迅速过时。让我们携手合作，共同创造更大影响！点击加入：Discord链接。

我们的核心团队（按字母顺序排列）

研究团队	工程团队	产品管理	用户体验设计
Myeongho Jeong	Geon Kim	Bokyung Huh	Eunsue Choi
Seungduk Kim	Rifqi Alfi
Seungtaek Choi	Sanghoon Han
	Suhyun Kang

模型简介

本模型是基于yanolja/EEVE-Korean-10.8B-v1.0进行微调的版本，该模型是upstage/SOLAR-10.7B-v1.0的韩语词汇扩展版。我们特别通过Axolotl平台采用了直接偏好优化（DPO）技术进行训练。

更多技术细节请参阅我们的研究报告：面向多语言大语言模型的高效词汇扩展方法。

提示词模板

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
Human: {prompt}
Assistant:

使用方法

from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("yanolja/EEVE-Korean-Instruct-10.8B-v1.0")
tokenizer = AutoTokenizer.from_pretrained("yanolja/EEVE-Korean-Instruct-10.8B-v1.0")

prompt_template = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\nHuman: {prompt}\nAssistant:\n"
text = '한국의 수도는 어디인가요? 아래 선택지 중 골라주세요.\n\n(A) 경성\n(B) 부산\n(C) 평양\n(D) 서울\n(E) 전주'
model_inputs = tokenizer(prompt_template.format(prompt=text), return_tensors='pt')

outputs = model.generate(**model_inputs, max_new_tokens=256)
output_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
print(output_text)

示例输出

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
Human: 한국의 수도는 어디인가요? 아래 선택지 중 골라주세요.

(A) 경성
(B) 부산
(C) 평양
(D) 서울
(E) 전주
Assistant:
(D) 서울이 한국의 수도입니다. 서울은 나라의 북동부에 위치해 있으며, 정치, 경제, 문화의 중심지입니다. 약 1,000만 명이 넘는 인구를 가진 세계에서 가장 큰 도시 중 하나입니다. 서울은 높은 빌딩, 현대적인 인프라, 활기 문화 장면으로 유명합니다. 또한, 많은 역사적 명소와 박물관이 있어 방문객들에게 풍부한 문화 체험을 제공합니다.

训练数据

• Open-Orca/SlimOrca-Dedup 的韩语翻译版本
  • argilla/ultrafeedback-binarized-preferences-cleaned 的韩语翻译版本
  • 未使用其他数据集

引用文献

@misc{kim2024efficient,
      title={Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models}, 
      author={Seungduk Kim and Seungtaek Choi and Myeongho Jeong},
      year={2024},
      eprint={2402.14714},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{cui2023ultrafeedback,
      title={UltraFeedback: Boosting Language Models with High-quality Feedback}, 
      author={Ganqu Cui and Lifan Yuan and Ning Ding and Guanming Yao and Wei Zhu and Yuan Ni and Guotong Xie and Zhiyuan Liu and Maosong Sun},
      year={2023},
      eprint={2310.01377},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{SlimOrcaDedup,
  title = {SlimOrca Dedup: A Deduplicated Subset of SlimOrca},
  author = {Wing Lian and Guan Wang and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium" and Nathan Hoos},
  year = {2023},
  publisher = {HuggingFace},
  url = {https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup/}
}

@misc{mukherjee2023orca,
      title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, 
      author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
      year={2023},
      eprint={2306.02707},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

开放大语言模型排行榜评估结果

详细结果可查阅此处

评测指标	数值
平均得分	66.48
AI2推理挑战赛（25样本）	64.85
HellaSwag（10样本）	83.04
MMLU（5样本）	64.23
TruthfulQA（0样本）	54.09
Winogrande（5样本）	81.93
GSM8k（5样本）	50.72