PrompTartLAB/Llama3ko_8B_inst_PTT_enko

Llama-3-KoEn-8B-Instruct-preview Fine-Tuned on Parenthetical Terminology Translation (PTT) Dataset

Model Overview

This is a Llama-3-KoEn-8B-Instruct-preview model fine-tuned on the Parenthetical Terminology Translation (PTT) dataset. The PTT dataset focuses on translating technical terms accurately by placing the original English term in parentheses alongside its Korean translation, enhancing clarity and precision in specialized fields. This fine-tuned model is optimized for handling technical terminology in the Artificial Intelligence (AI) domain.

Example Usage

Here’s how to use this fine-tuned model with the Hugging Face transformers library:

import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load Model and Tokenizer
model_name = "PrompTartLAB/Llama3ko_8B_inst_PTT_enko"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Example sentence
text = "The model was fine-tuned using knowledge distillation techniques. The training dataset was created using a collaborative multi-agent framework powered by large language models."
prompt = f"Translate input sentence to Korean \n### Input: {text} \n### Translated:"

# Tokenize and generate translation
input_ids = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**input_ids, max_new_tokens=1024)
out_message = tokenizer.decode(outputs[0][len(input_ids["input_ids"][0]):], skip_special_tokens=True)

# " 이 모델은 지식 증류 기법(knowledge distillation techniques)을 사용하여 미세 조정되었습니다. 훈련 데이터셋은 대형 언어 모델(large language models)로 구동되는 협력적 다중 에이전트 프레임워크(collaborative multi-agent framework)를 사용하여 생성되었습니다."

Limitations

• Out-of-Domain Accuracy: While the model generalizes to some extent, accuracy may vary in domains that were not part of the training set.
• Incomplete Parenthetical Annotation: Not all technical terms are consistently displayed in parentheses; in some cases, terms may be omitted or not annotated as expected.

Citation

If you use this model in your research, please cite the original dataset and paper:

@misc{myung2024efficienttechnicaltermtranslation,
      title={Efficient Technical Term Translation: A Knowledge Distillation Approach for Parenthetical Terminology Translation}, 
      author={Jiyoon Myung and Jihyeon Park and Jungki Son and Kyungro Lee and Joohyung Han},
      year={2024},
      eprint={2410.00683},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.00683}, 
}

Contact

For questions or feedback, please contact [email protected].