mjk0618 commited on
Commit
b611c10
โ€ข
1 Parent(s): 659b9d2

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +42 -0
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ - en
5
+ metrics:
6
+ - bleu
7
+ pipeline_tag: translation
8
+ tags:
9
+ - science
10
+ - technology
11
+ ---
12
+
13
+ # Model Overview
14
+ This model is fine-tuned model of "Helsinki-NLP/opus-mt-ko-en" <br/>
15
+ The model has been trained with 1,198,943 Korean, Enlgish sentence pairs which mainly contains science, technology terms.
16
+
17
+ # Load Model
18
+ ```
19
+ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
20
+
21
+ tokenizer = AutoTokenizer.from_pretrained("mjk0618/mt-ko-en-scitech")
22
+ model = AutoModelForSeq2SeqLM.from_pretrained("mjk0618/mt-ko-en-scitech")
23
+ ```
24
+
25
+ # How to use
26
+ ```
27
+ # After loading model
28
+ # Define the text you want to translate
29
+ sentence = "์ธ๊ณต์ง€๋Šฅ์€ ์ธ๊ฐ„์˜ ํ•™์Šต๋Šฅ๋ ฅ, ์ถ”๋ก ๋Šฅ๋ ฅ, ์ง€๊ฐ๋Šฅ๋ ฅ์„ ์ธ๊ณต์ ์œผ๋กœ ๊ตฌํ˜„ํ•˜๋ ค๋Š” ์ปดํ“จํ„ฐ ๊ณผํ•™์˜ ์„ธ๋ถ€๋ถ„์•ผ ์ค‘ ํ•˜๋‚˜์ด๋‹ค"
30
+
31
+ # Tokenize the text
32
+ inputs = tokenizer(sentence, return_tensors="pt").input_ids
33
+
34
+ # Generate the translated text
35
+ outputs = model.generate(inputs)[0]
36
+
37
+ # Decode the translated text
38
+ translated_sentence = tokenizer.decode(outputs, skip_special_tokens=True)
39
+
40
+ print(translated_sentence)
41
+ # Artificial intelligence is one of the details of computer science that artifically implements human learning ability, reasoning ability, and perception ability.
42
+ ```