EEVE Korean Instruct 2.8B V1.0

🚀 EEVE-Korean-Instruct-2.8B-v1.0

EEVE-Korean-Instruct-2.8B-v1.0 是基于大语言模型领域开发的模型，它在特定基础模型上进行微调，适用于韩语相关的语言处理任务，为韩语语言交互等场景提供支持。

🚀 快速开始

加入我们的 Discord 社区！

如果您对大语言模型领域充满热情，希望交流知识和见解，我们诚挚地邀请您加入我们的 Discord 服务器。值得注意的是，该服务器主要使用韩语。大语言模型的发展日新月异，如果不积极分享，我们的知识很快就会过时。让我们携手合作，共同产生更大的影响！点击此处加入：Discord 链接。

✨ 主要特性

团队信息

模型介绍

该模型是 yanolja/EEVE-Korean-2.8B-v1.0 的微调版本，而 yanolja/EEVE-Korean-2.8B-v1.0 是 microsoft/phi-2 的韩语词汇扩展版本。具体来说，我们通过 Axolotl 使用了直接偏好优化（DPO）方法。

更多详细信息，请参考我们的技术报告：Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models。

提示模板

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:

📦 安装指南

文档未提供安装步骤，暂不展示。

💻 使用示例

基础用法

from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("yanolja/EEVE-Korean-Instruct-2.8B-v1.0", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("yanolja/EEVE-Korean-Instruct-2.8B-v1.0", trust_remote_code=True)

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:
한국의 수도는 (D) 서울입니다. 서울은 수도권과 수도권 내의 주요 도시들을 포함하는 광역 행정구역으로, 대한민국의 수도입니다. 서울은 수도권 인구의 약 70%를 차지하며, 대한민국의 경제, 정치, 문화의 중심지입니다.

📚 详细文档

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

引用信息

@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}
}

Open LLM Leaderboard Evaluation Results

详细结果可在 此处 查看。

📄 许可证

本项目采用 Apache-2.0 许可证。