nayohan's picture
Update README.md
8b06ed5 verified
---
language:
- en
- ko
license: llama3
library_name: transformers
tags:
- translation
- enko
- ko
base_model:
- meta-llama/Meta-Llama-3-8B-Instruct
datasets:
- squarelike/sharegpt_deepl_ko_translation
pipeline_tag: text-generation
---
# **Introduction**
This model was trained to translate a sentence from English to Korean using the 486k dataset from [squarelike/sharegpt_deepl_ko_translation](https://huggingface.co/datasets/nayohan/aihub-en-ko-translation-1.2m).
### **Loading the Model**
Use the following Python code to load the model:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "nayohan/llama3-8b-it-translation-sharegpt-en-ko"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
device_map="auto",
torch_dtype=torch.bfloat16
)
```
### **Generating Text**
This model supports translation from English to Korean. To generate text, use the following Python code:
```python
system_prompt="๋‹น์‹ ์€ ๋ฒˆ์—ญ๊ธฐ ์ž…๋‹ˆ๋‹ค. ์˜์–ด๋ฅผ ํ•œ๊ตญ์–ด๋กœ ๋ฒˆ์—ญํ•˜์„ธ์š”."
sentence = "The aerospace industry is a flower in the field of technology and science."
conversation = [{'role': 'system', 'content': system_prompt},
{'role': 'user', 'content': sentence}]
inputs = tokenizer.apply_chat_template(
conversation,
tokenize=True,
add_generation_prompt=True,
return_tensors='pt'
).to("cuda")
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][len(inputs[0]):]))
```
```
# Result
# INPUT: <|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nActs as a translator. Translate en sentences into ko sentences in colloquial style.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nThe aerospace industry is a flower in the field of technology and science.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n
# OUTPUT: ํ•ญ๊ณต์šฐ์ฃผ ์‚ฐ์—…์€ ๊ธฐ์ˆ ๊ณผ ๊ณผํ•™ ๋ถ„์•ผ์˜ ๊ฝƒ์ž…๋‹ˆ๋‹ค.<|eot_id|>
# INPUT:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n๋‹น์‹ ์€ ๋ฒˆ์—ญ๊ธฐ ์ž…๋‹ˆ๋‹ค. ์˜์–ด๋ฅผ ํ•œ๊ตญ์–ด๋กœ ๋ฒˆ์—ญํ•˜์„ธ์š”.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n
Technical and basic sciences are very important in terms of research. It has a significant impact on the industrial development of a country. Government policies control the research budget.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n
# OUTPUT: ๊ธฐ์ˆ  ๋ฐ ๊ธฐ์ดˆ ๊ณผํ•™์€ ์—ฐ๊ตฌ ์ธก๋ฉด์—์„œ ๋งค์šฐ ์ค‘์š”ํ•ฉ๋‹ˆ๋‹ค. ์ด๋Š” ํ•œ ๊ตญ๊ฐ€์˜ ์‚ฐ์—… ๋ฐœ์ „์— ํฐ ์˜ํ–ฅ์„ ๋ฏธ์นฉ๋‹ˆ๋‹ค. ์ •๋ถ€ ์ •์ฑ…์— ๋”ฐ๋ผ ์—ฐ๊ตฌ ์˜ˆ์‚ฐ์ด ๊ฒฐ์ •๋ฉ๋‹ˆ๋‹ค.<|eot_id|>
```
### **Citation**
```bibtex
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url={https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
```
Our trainig code can be found here: [TBD]