Translation
Transformers
PyTorch
Safetensors
Korean
English
marian
text2text-generation
science
technology
Instructions to use mjk0618/mt-ko-en-scitech with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mjk0618/mt-ko-en-scitech with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="mjk0618/mt-ko-en-scitech")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("mjk0618/mt-ko-en-scitech") model = AutoModelForMultimodalLM.from_pretrained("mjk0618/mt-ko-en-scitech") - Notebooks
- Google Colab
- Kaggle
Model Overview
This model is fine-tuned model of "Helsinki-NLP/opus-mt-ko-en"
The model is trained with 1,198,943 Korean-English sentence pairs which mainly contains science, technology terms.
Load Model
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("mjk0618/mt-ko-en-scitech")
model = AutoModelForSeq2SeqLM.from_pretrained("mjk0618/mt-ko-en-scitech")
How to use
# After loading model
sentence = "์ธ๊ณต์ง๋ฅ์ ์ธ๊ฐ์ ํ์ต๋ฅ๋ ฅ, ์ถ๋ก ๋ฅ๋ ฅ, ์ง๊ฐ๋ฅ๋ ฅ์ ์ธ๊ณต์ ์ผ๋ก ๊ตฌํํ๋ ค๋ ์ปดํจํฐ ๊ณผํ์ ์ธ๋ถ๋ถ์ผ ์ค ํ๋์ด๋ค"
inputs = tokenizer(sentence, return_tensors="pt").input_ids
outputs = model.generate(inputs)[0]
translated_sentence = tokenizer.decode(outputs, skip_special_tokens=True)
print(translated_sentence)
# Artificial intelligence is one of the details of computer science that artifically implements human learning ability, reasoning ability, and perception ability.
- Downloads last month
- 4