đ EEVE-Korean-Instruct-10.8B-v1.0
This is a fine - tuned large language model based on Korean vocabulary extension, which can provide high - quality language interaction services.

đ Quick Start
This model is a fine - tuned version of yanolja/EEVE - Korean - 10.8B - v1.0, which is a Korean vocabulary - extended version of upstage/SOLAR - 10.7B - v1.0. Specifically, we utilized Direct Preference Optimization (DPO) through the use of Axolotl.
For more details, please refer to our technical report: Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models.
⨠Features
Community Engagement
If you're passionate about the field of Large Language Models and wish to exchange knowledge and insights, we warmly invite you to join our Discord server. It's worth noting that Korean is the primary language used in this server. The landscape of LLM is evolving rapidly, and without active sharing, our collective knowledge risks becoming outdated swiftly. Let's collaborate and drive greater impact together! Join us here: Discord Link.
Dedicated Team
Research |
Engineering |
Product Management |
UX Design |
Myeongho Jeong |
Geon Kim |
Bokyung Huh |
Eunsue Choi |
Seungduk Kim |
Rifqi Alfi |
|
|
Seungtaek Choi |
Sanghoon Han |
|
|
|
Suhyun Kang |
|
|
đŚ Installation
No specific installation steps are provided in the original document.
đť Usage Examples
Basic Usage
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 = 'íęľě ěëë ě´ëě¸ę°ě? ěë ě íě§ ě¤ ęł¨ëźěŁźě¸ě.\n\n(A) 경ěą\n(B) ëśě°\n(C) íě\n(D) ěě¸\n(E) ě 죟'
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)
Example Output
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: íęľě ěëë ě´ëě¸ę°ě? ěë ě íě§ ě¤ ęł¨ëźěŁźě¸ě.
(A) 경ěą
(B) ëśě°
(C) íě
(D) ěě¸
(E) ě 죟
Assistant:
(D) ěě¸ě´ íęľě ěëě
ëë¤. ěě¸ě ëëźě ëśëëśě ěěší´ ěěźëа, ě ěš, 경ě , 돸íě ě¤ěŹě§ě
ëë¤. ě˝ 1,000ë§ ëŞ
ě´ ëë ě¸ęľŹëĽź ę°ě§ ě¸ęłěě ę°ěĽ í° ëě ě¤ íëě
ëë¤. ěě¸ě ëě ëšëŠ, íëě ě¸ ě¸íëź, í기 돸í ěĽëŠ´ěźëĄ ě ëŞ
íŠëë¤. ëí, ë§ě ěěŹě ëŞ
ěě ë°ëŹźę´ě´ ěě´ ë°ŠëŹ¸ę°ë¤ěę˛ íëśí 돸í 체íě ě ęłľíŠëë¤.
đ Documentation
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.
Human: {prompt}
Assistant:
Training Data
Evaluation Results
Detailed results can be found here
Metric |
Value |
Avg. |
66.48 |
AI2 Reasoning Challenge (25 - Shot) |
64.85 |
HellaSwag (10 - Shot) |
83.04 |
MMLU (5 - Shot) |
64.23 |
TruthfulQA (0 - shot) |
54.09 |
Winogrande (5 - shot) |
81.93 |
GSM8k (5 - shot) |
50.72 |
đ§ Technical Details
No specific technical details are provided in the original document.
đ License
The model is released under the Apache - 2.0 license.
đ Citation
@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}
}