Saxo commited on
Commit
4d78c76
โ€ข
1 Parent(s): bb6e32b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ pipeline_tag: text-generation
18
 
19
 
20
  AI ์™€ ๋น…๋ฐ์ดํ„ฐ ๋ถ„์„ ์ „๋ฌธ ๊ธฐ์—…์ธ Linkbricks์˜ ๋ฐ์ดํ„ฐ์‚ฌ์ด์–ธํ‹ฐ์ŠคํŠธ์ธ ์ง€์œค์„ฑ ๋ฐ•์‚ฌ(Saxo)๊ฐ€ meta-llama/Meta-Llama-3-8B๋ฅผ ๋ฒ ์ด์Šค๋ชจ๋ธ๋กœ GCP์ƒ์˜ H100-80G 8๊ฐœ๋ฅผ ํ†ตํ•ด SFT-DPO ํ›ˆ๋ จ์„ ํ•œ(8000 Tokens) ํ•œ๊ธ€ ๊ธฐ๋ฐ˜ ๋ชจ๋ธ.
21
- ํ† ํฌ๋‚˜์ด์ €๋Š” ๋ผ๋งˆ3๋ž‘ ๋™์ผํ•˜๋ฉฐ ํ•œ๊ธ€ VOCA ํ™•์žฅ์€ ํ•˜์ง€ ์•Š์€ ๋ฒ„์ „ ์ž…๋‹ˆ๋‹ค. ํ•œ๊ธ€์ด 20๋งŒ๊ฐœ ์ด์ƒ ํฌํ•จ๋œ ํ•œ๊ธ€์ „์šฉ ํ† ํฌ๋‚˜์ด์ € ๋ชจ๋ธ์€ ๋ณ„๋„ ์—ฐ๋ฝ ํ•˜์‹œ๋ฉด ๋ฉ๋‹ˆ๋‹ค.
22
 
23
  Dr. Yunsung Ji (Saxo), a data scientist at Linkbricks, a company specializing in AI and big data analytics, trained the meta-llama/Meta-Llama-3-8B base model on 8 H100-60Gs on GCP for 4 hours of instructional training (8000 Tokens).
24
  Accelerate, Deepspeed Zero-3 libraries were used.
 
18
 
19
 
20
  AI ์™€ ๋น…๋ฐ์ดํ„ฐ ๋ถ„์„ ์ „๋ฌธ ๊ธฐ์—…์ธ Linkbricks์˜ ๋ฐ์ดํ„ฐ์‚ฌ์ด์–ธํ‹ฐ์ŠคํŠธ์ธ ์ง€์œค์„ฑ ๋ฐ•์‚ฌ(Saxo)๊ฐ€ meta-llama/Meta-Llama-3-8B๋ฅผ ๋ฒ ์ด์Šค๋ชจ๋ธ๋กœ GCP์ƒ์˜ H100-80G 8๊ฐœ๋ฅผ ํ†ตํ•ด SFT-DPO ํ›ˆ๋ จ์„ ํ•œ(8000 Tokens) ํ•œ๊ธ€ ๊ธฐ๋ฐ˜ ๋ชจ๋ธ.
21
+ ํ† ํฌ๋‚˜์ด์ €๋Š” ๋ผ๋งˆ3๋ž‘ ๋™์ผํ•˜๋ฉฐ ํ•œ๊ธ€ VOCA ํ™•์žฅ์€ ํ•˜์ง€ ์•Š์€ ๋ฒ„์ „ ์ž…๋‹ˆ๋‹ค. ํ•œ๊ธ€์ด 20๋งŒ๊ฐœ ์ด์ƒ ํฌํ•จ๋œ ํ•œ๊ธ€์ „์šฉ ํ† ํฌ๋‚˜์ด์ € ๋ชจ๋ธ์€ ๋ณ„๋„ ์—ฐ๋ฝ ์ฃผ์‹œ๊ธฐ ๋ฐ”๋ž๋‹ˆ๋‹ค.
22
 
23
  Dr. Yunsung Ji (Saxo), a data scientist at Linkbricks, a company specializing in AI and big data analytics, trained the meta-llama/Meta-Llama-3-8B base model on 8 H100-60Gs on GCP for 4 hours of instructional training (8000 Tokens).
24
  Accelerate, Deepspeed Zero-3 libraries were used.