jujbob commited on
Commit
ae50909
โ€ข
1 Parent(s): 17ecd35

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -4
README.md CHANGED
@@ -16,19 +16,22 @@ base_model:
16
 
17
 
18
  ```bash
19
- ์ €ํฌ ์„œ์šธ๊ณผ๊ธฐ๋Œ€ MLP์—ฐ๊ตฌ์‹ค์—์„œ ํ•œ๊ตญ์–ด-์˜์–ด ์ด์ค‘ ์–ธ์–ด๋ชจ๋ธ์ธ Bllossom์„ ๊ณต๊ฐœํ–ˆ์Šต๋‹ˆ๋‹ค! ์„œ์šธ๊ณผ๊ธฐ๋Œ€ ์Šˆํผ์ปดํ“จํŒ… ์„ผํ„ฐ์˜ ์ง€์›์œผ๋กœ 100GB๊ฐ€๋„˜๋Š” ํ•œ๊ตญ์–ด ์ถ”๊ฐ€ํ•™์Šต์„ ์ง„ํ–‰ํ•œ ํ•œ๊ตญ์–ด ๊ฐ•ํ™” ์ด์ค‘์–ธ์–ด ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค!
 
20
  ํ•œ๊ตญ์–ด ์ž˜ํ•˜๋Š” ๋ชจ๋ธ ์ฐพ๊ณ  ์žˆ์ง€ ์•Š์œผ์…จ๋‚˜์š”?
21
- - ๋ฌด๋ ค 3๋งŒ๊ฐœ๊ฐ€ ๋„˜๋Š” ํ•œ๊ตญ์–ด ์–ดํœ˜ํ™•์žฅ
22
  - Llama3๋Œ€๋น„ ๋Œ€๋žต 25% ๋” ๊ธด ๊ธธ์ด์˜ ํ•œ๊ตญ์–ด Context ์ฒ˜๋ฆฌ๊ฐ€๋Šฅ
23
  - ํ•œ๊ตญ์–ด-์˜์–ด Pararell Corpus๋ฅผ ํ™œ์šฉํ•œ ํ•œ๊ตญ์–ด-์˜์–ด ์ง€์‹์—ฐ๊ฒฐ (์‚ฌ์ „ํ•™์Šต)
24
  - ํ•œ๊ตญ์–ด ๋ฌธํ™”, ์–ธ์–ด๋ฅผ ๊ณ ๋ คํ•ด ์–ธ์–ดํ•™์ž๊ฐ€ ์ œ์ž‘ํ•œ ๋ฐ์ดํ„ฐ๋ฅผ ํ™œ์šฉํ•œ ๋ฏธ์„ธ์กฐ์ •
25
  - ๊ฐ•ํ™”ํ•™์Šต
26
- ์ด ๋ชจ๋“ ๊ฒŒ ํ•œ๊บผ๋ฒˆ์— ์ ์šฉ๋˜๊ณ  ์ƒ์—…์  ์ด์šฉ์ด ๊ฐ€๋Šฅํ•œ Bllossom์„ ์ด์šฉํ•ด ์—ฌ๋Ÿฌ๋ถ„ ๋งŒ์˜ ๋ชจ๋ธ์„ ๋งŒ๋“ค์–ด๋ณด์„ธ์šฅ! ๋ฌด๋ ค Colab ๋ฌด๋ฃŒ GPU๋กœ ํ•™์Šต์ด ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค.
 
27
 
28
  1. Bllossom-8B๋Š” ์„œ์šธ๊ณผ๊ธฐ๋Œ€, ํ…Œ๋””์ธ, ์—ฐ์„ธ๋Œ€ ์–ธ์–ด์ž์› ์—ฐ๊ตฌ์‹ค์˜ ์–ธ์–ดํ•™์ž์™€ ํ˜‘์—…ํ•ด ๋งŒ๋“  ์‹ค์šฉ์ฃผ์˜๊ธฐ๋ฐ˜ ์–ธ์–ด๋ชจ๋ธ์ž…๋‹ˆ๋‹ค! ์•ž์œผ๋กœ ์ง€์†์ ์ธ ์—…๋ฐ์ดํŠธ๋ฅผ ํ†ตํ•ด ๊ด€๋ฆฌํ•˜๊ฒ ์Šต๋‹ˆ๋‹ค ๋งŽ์ด ํ™œ์šฉํ•ด์ฃผ์„ธ์š” ๐Ÿ™‚
29
  2. ์ดˆ ๊ฐ•๋ ฅํ•œ Advanced-Bllossom 8B, 70B๋ชจ๋ธ, ์‹œ๊ฐ-์–ธ์–ด๋ชจ๋ธ์„ ๋ณด์œ ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค! (๊ถ๊ธˆํ•˜์‹ ๋ถ„์€ ๊ฐœ๋ณ„ ์—ฐ๋ฝ์ฃผ์„ธ์š”!!)
30
  3. Bllossom์€ NAACL2024, LREC-COLING2024 (๊ตฌ๋‘) ๋ฐœํ‘œ๋กœ ์ฑ„ํƒ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
31
- 4. ์ข‹์€ ์–ธ์–ด๋ชจ๋ธ ๊ณ„์† ์—…๋ฐ์ดํŠธ ํ•˜๊ฒ ์Šต๋‹ˆ๋‹ค!! ํ•œ๊ตญ์–ด ๊ฐ•ํ™”๋ฅผ์œ„ํ•ด ๊ณต๋™ ์—ฐ๊ตฌํ•˜์‹ค๋ถ„(ํŠนํžˆ๋…ผ๋ฌธ) ์–ธ์ œ๋“  ํ™˜์˜ํ•ฉ๋‹ˆ๋‹ค!! ํŠนํžˆ ์†Œ๋Ÿ‰์˜ GPU๋ผ๋„ ๋Œ€์—ฌ ๊ฐ€๋Šฅํ•œํŒ€์€ ์–ธ์ œ๋“  ์—ฐ๋ฝ์ฃผ์„ธ์š”! ๋งŒ๋“ค๊ณ  ์‹ถ์€๊ฑฐ ๋„์™€๋“œ๋ ค์š”.
 
32
  ```
33
 
34
  The Bllossom language model is a Korean-English bilingual language model based on the open-source LLama3. It enhances the connection of knowledge between Korean and English. It has the following features:
 
16
 
17
 
18
  ```bash
19
+ ์ €ํฌ ์„œ์šธ๊ณผ๊ธฐ๋Œ€ MLP์—ฐ๊ตฌ์‹ค์—์„œ ํ•œ๊ตญ์–ด-์˜์–ด ์ด์ค‘ ์–ธ์–ด๋ชจ๋ธ์ธ Bllossom์„ ๊ณต๊ฐœํ–ˆ์Šต๋‹ˆ๋‹ค!
20
+ ์„œ์šธ๊ณผ๊ธฐ๋Œ€ ์Šˆํผ์ปดํ“จํŒ… ์„ผํ„ฐ์˜ ์ง€์›์œผ๋กœ 100GB๊ฐ€๋„˜๋Š” ํ•œ๊ตญ์–ด ์ถ”๊ฐ€ํ•™์Šต์„ ์ง„ํ–‰ํ•œ ํ•œ๊ตญ์–ด ๊ฐ•ํ™” ์ด์ค‘์–ธ์–ด ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค!
21
  ํ•œ๊ตญ์–ด ์ž˜ํ•˜๋Š” ๋ชจ๋ธ ์ฐพ๊ณ  ์žˆ์ง€ ์•Š์œผ์…จ๋‚˜์š”?
22
+ - ํ•œ๊ตญ์–ด ์ตœ์ดˆ! ๋ฌด๋ ค 3๋งŒ๊ฐœ๊ฐ€ ๋„˜๋Š” ํ•œ๊ตญ์–ด ์–ดํœ˜ํ™•์žฅ
23
  - Llama3๋Œ€๋น„ ๋Œ€๋žต 25% ๋” ๊ธด ๊ธธ์ด์˜ ํ•œ๊ตญ์–ด Context ์ฒ˜๋ฆฌ๊ฐ€๋Šฅ
24
  - ํ•œ๊ตญ์–ด-์˜์–ด Pararell Corpus๋ฅผ ํ™œ์šฉํ•œ ํ•œ๊ตญ์–ด-์˜์–ด ์ง€์‹์—ฐ๊ฒฐ (์‚ฌ์ „ํ•™์Šต)
25
  - ํ•œ๊ตญ์–ด ๋ฌธํ™”, ์–ธ์–ด๋ฅผ ๊ณ ๋ คํ•ด ์–ธ์–ดํ•™์ž๊ฐ€ ์ œ์ž‘ํ•œ ๋ฐ์ดํ„ฐ๋ฅผ ํ™œ์šฉํ•œ ๋ฏธ์„ธ์กฐ์ •
26
  - ๊ฐ•ํ™”ํ•™์Šต
27
+ ์ด ๋ชจ๋“ ๊ฒŒ ํ•œ๊บผ๋ฒˆ์— ์ ์šฉ๋˜๊ณ  ์ƒ์—…์  ์ด์šฉ์ด ๊ฐ€๋Šฅํ•œ Bllossom์„ ์ด์šฉํ•ด ์—ฌ๋Ÿฌ๋ถ„ ๋งŒ์˜ ๋ชจ๋ธ์„ ๋งŒ๋“ค์–ด๋ณด์„ธ์šฅ!
28
+ ๋ฌด๋ ค Colab ๋ฌด๋ฃŒ GPU๋กœ ํ•™์Šต์ด ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค.
29
 
30
  1. Bllossom-8B๋Š” ์„œ์šธ๊ณผ๊ธฐ๋Œ€, ํ…Œ๋””์ธ, ์—ฐ์„ธ๋Œ€ ์–ธ์–ด์ž์› ์—ฐ๊ตฌ์‹ค์˜ ์–ธ์–ดํ•™์ž์™€ ํ˜‘์—…ํ•ด ๋งŒ๋“  ์‹ค์šฉ์ฃผ์˜๊ธฐ๋ฐ˜ ์–ธ์–ด๋ชจ๋ธ์ž…๋‹ˆ๋‹ค! ์•ž์œผ๋กœ ์ง€์†์ ์ธ ์—…๋ฐ์ดํŠธ๋ฅผ ํ†ตํ•ด ๊ด€๋ฆฌํ•˜๊ฒ ์Šต๋‹ˆ๋‹ค ๋งŽ์ด ํ™œ์šฉํ•ด์ฃผ์„ธ์š” ๐Ÿ™‚
31
  2. ์ดˆ ๊ฐ•๋ ฅํ•œ Advanced-Bllossom 8B, 70B๋ชจ๋ธ, ์‹œ๊ฐ-์–ธ์–ด๋ชจ๋ธ์„ ๋ณด์œ ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค! (๊ถ๊ธˆํ•˜์‹ ๋ถ„์€ ๊ฐœ๋ณ„ ์—ฐ๋ฝ์ฃผ์„ธ์š”!!)
32
  3. Bllossom์€ NAACL2024, LREC-COLING2024 (๊ตฌ๋‘) ๋ฐœํ‘œ๋กœ ์ฑ„ํƒ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
33
+ 4. ์ข‹์€ ์–ธ์–ด๋ชจ๋ธ ๊ณ„์† ์—…๋ฐ์ดํŠธ ํ•˜๊ฒ ์Šต๋‹ˆ๋‹ค!! ํ•œ๊ตญ์–ด ๊ฐ•ํ™”๋ฅผ์œ„ํ•ด ๊ณต๋™ ์—ฐ๊ตฌํ•˜์‹ค๋ถ„(ํŠนํžˆ๋…ผ๋ฌธ) ์–ธ์ œ๋“  ํ™˜์˜ํ•ฉ๋‹ˆ๋‹ค!!
34
+ ํŠนํžˆ ์†Œ๋Ÿ‰์˜ GPU๋ผ๋„ ๋Œ€์—ฌ ๊ฐ€๋Šฅํ•œํŒ€์€ ์–ธ์ œ๋“  ์—ฐ๋ฝ์ฃผ์„ธ์š”! ๋งŒ๋“ค๊ณ  ์‹ถ์€๊ฑฐ ๋„์™€๋“œ๋ ค์š”.
35
  ```
36
 
37
  The Bllossom language model is a Korean-English bilingual language model based on the open-source LLama3. It enhances the connection of knowledge between Korean and English. It has the following features: