Seagull-13b-translation

Seagull-13b-translation 📇

Seagull-13b-translation is yet another translator model, but carefully considered the following issues from existing translation models.

• Exact match of newline or space
• Not using dataset with first letter removed
• Code
• Markdown format
• LaTeX format
• etc

이런 이슈들을 충분히 체크하고 학습을 진행하였지만, 모델을 사용할 때는 이런 부분에 대한 결과를 면밀하게 살펴보는 것을 추천합니다(코드가 포함된 텍스트 등).

If you're interested in building large-scale language models to solve a wide variety of problems in a wide variety of domains, you should consider joining Allganize. For a coffee chat or if you have any questions, please do not hesitate to contact me as well! - [email protected]

This model was created as a personal experiment, unrelated to the organization I work for.

License

From original model author:

• Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License, under LLAMA 2 COMMUNITY LICENSE AGREEMENT
• Full License available at: https://huggingface.co/beomi/llama-2-koen-13b/blob/main/LICENSE

Model Details

Developed by

Jisoo Kim(kuotient)

Base Model

beomi/llama-2-koen-13b

Datasets

• sharegpt_deepl_ko_translation
• KOR-OpenOrca-Platypus-v3
• AIHUB
  • 기술과학 분야 한-영 번역 병렬 말뭉치 데이터
  • 일상생활 및 구어체 한-영 번역 병렬 말뭉치 데이터

Usage

Format

It follows only ChatML format.

<|im_start|>system
주어진 문장을 한국어로 번역하세요.<|im_end|>
<|im_start|>user
{instruction}<|im_end|>
<|im_start|>assistant
# Don't miss newline here

<|im_start|>system
주어진 문장을 영어로 번역하세요.<|im_end|>
<|im_start|>user
{instruction}<|im_end|>
<|im_start|>assistant
# Don't miss newline here

Output example

원문:

A particle's wave function, $\psi(x)$, is given by $$\psi(x)=\begin{cases} 3x & \text{if } -1 \leq x \leq 0 \ 3(1-x) & \text{if } 0 < x \leq 1 \ 0 & \text{otherwise} \end{cases}$$ Compute the Fourier transform, $\tilde{\psi}(k)$, of the wave function $\psi(x)$ and show that it satisfies the Fourier inversion theorem, i.e., $\psi(x) = \frac{1}{\sqrt{2\pi}} \int_{-\infty}^{\infty} \tilde{\psi}(k) e^{ikx} \mathrm{d}k$.

Seagull-13b-translation:

입자의 파동 함수 $\psi(x)$는 다음과 같이 주어집니다. $$\psi(x)=\begin{cases} 3x & \text{if } -1 \leq x \leq 0 \ 3(1-x) & \text{if } 0 < x \leq 1 \ 0 & \text{otherwise} \end{cases}$$ 파동 함수 $\psi(x)$의 푸리에 변환 $\tilde{\psi}(k)$를 계산하고 푸리에 반전 정리, 즉 $\psi(x) = \frac{1}{\sqrt{2\pi}} \int_{-\infty}^{\infty} \tilde{\psi}(k) e^{ikx} \mathrm{d}k$를 만족합니다.

DeepL:

입자의 파동 함수 $\psi(x)$는 $$\psi(x)=\begin{cases}로 주어집니다. 3x & \text{if } -1 \leq x \leq 0 \ 3(1-x) & \text{if } 0 < x \leq 1 \ 0 & \text{기타} \end{cases}$$ 파동 함수 $\psi(x)$의 푸리에 변환인 $\tilde{\psi}(k)$를 계산하고 푸리에 반전 정리, 즉 $\psi(x) = \frac{1}{\sqrt{2\pi}}를 만족함을 증명합니다. \int_{-\infty}^{\infty} \물결표{\psi}(k) e^{ikx} \mathrm{d}k$.

...and much more awesome cases with SQL query, code and markdown!

How to

I highly recommend to inference model with vllm. I will write a guide for quick and easy inference if requested. Since, chat_template already contains insturction format above. You can use the code below.

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("kuotient/Seagull-13B-translation")
tokenizer = AutoTokenizer.from_pretrained("kuotient/Seagull-13B-translation")
messages = [
    {"role": "system", "content", "주어진 문장을 한국어로 번역하세요."}
    {"role": "user", "content": "Here are five examples of nutritious foods to serve your kids."},
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])